GtFeatureIndex *agn_import_simple(int numfiles, const char **filenames,
char *type, AgnLogger *logger)
{
GtFeatureIndex *features = gt_feature_index_memory_new();
GtNodeStream *gff3 = gt_gff3_in_stream_new_unsorted(numfiles, filenames);
gt_gff3_in_stream_check_id_attributes((GtGFF3InStream *)gff3);
gt_gff3_in_stream_enable_tidy_mode((GtGFF3InStream *)gff3);
GtHashmap *typestokeep = gt_hashmap_new(GT_HASH_STRING, NULL, NULL);
gt_hashmap_add(typestokeep, type, type);
GtNodeStream *filterstream = agn_filter_stream_new(gff3, typestokeep);
GtNodeStream *featstream = gt_feature_out_stream_new(filterstream, features);
GtError *error = gt_error_new();
int result = gt_node_stream_pull(featstream, error);
if(result == -1)
{
agn_logger_log_error(logger, "error processing node stream: %s",
gt_error_get(error));
}
gt_error_delete(error);
if(agn_logger_has_error(logger))
{
gt_feature_index_delete(features);
features = NULL;
}
gt_node_stream_delete(gff3);
gt_node_stream_delete(filterstream);
gt_node_stream_delete(featstream);
return features;
}
int gt_gff3_to_gtf(int argc, const char **argv, GtError *err)
{
GtNodeStream *gff3_in_stream = NULL, *gtf_out_stream = NULL;
int parsed_args, had_err = 0;
gt_error_check(err);
/* option parsing */
switch (parse_options(&parsed_args, argc, argv, err)) {
case OPTIONPARSER_OK: break;
case OPTIONPARSER_ERROR: return -1;
case OPTIONPARSER_REQUESTS_EXIT: return 0;
}
/* create a gff3 input stream */
gff3_in_stream = gt_gff3_in_stream_new_unsorted(argc - parsed_args,
argv + parsed_args);
if (!gff3_in_stream)
had_err = -1;
if (!had_err) {
/* create a gtf output stream */
gtf_out_stream = gt_gtf_out_stream_new(gff3_in_stream, NULL);
/* pull the features through the stream and free them afterwards */
had_err = gt_node_stream_pull(gtf_out_stream, err);
}
/* free */
gt_node_stream_delete(gff3_in_stream);
gt_node_stream_delete(gtf_out_stream);
return had_err;
}
GtFeatureIndex *agn_import_canonical(int numfiles, const char **filenames,
AgnLogger *logger)
{
GtNodeStream *gff3 = gt_gff3_in_stream_new_unsorted(numfiles, filenames);
gt_gff3_in_stream_check_id_attributes((GtGFF3InStream *)gff3);
gt_gff3_in_stream_enable_tidy_mode((GtGFF3InStream *)gff3);
GtFeatureIndex *features = gt_feature_index_memory_new();
GtNodeStream *cgstream = agn_canon_gene_stream_new(gff3, logger);
GtNodeStream *featstream = gt_feature_out_stream_new(cgstream, features);
GtError *error = gt_error_new();
int result = gt_node_stream_pull(featstream, error);
if(result == -1)
{
agn_logger_log_error(logger, "error processing node stream: %s",
gt_error_get(error));
}
gt_error_delete(error);
if(agn_logger_has_error(logger))
{
gt_feature_index_delete(features);
features = NULL;
}
gt_node_stream_delete(gff3);
gt_node_stream_delete(cgstream);
gt_node_stream_delete(featstream);
return features;
}
static int gt_seqids_runner(GT_UNUSED int argc, const char **argv,
int parsed_args,
GT_UNUSED void *tool_arguments, GtError *err)
{
GtNodeStream *in_stream, *v_stream;
GtCstrTable *cst;
int had_err = 0;
gt_error_check(err);
cst = gt_cstr_table_new();
in_stream = gt_gff3_in_stream_new_unsorted(argc - parsed_args,
argv + parsed_args);
v_stream = gt_visitor_stream_new(in_stream, gt_collect_ids_visitor_new(cst));
had_err = gt_node_stream_pull(v_stream, err);
if (!had_err) {
GtStrArray *seqids;
GtUword i;
seqids = gt_cstr_table_get_all(cst);
for (i = 0; i < gt_str_array_size(seqids); i++) {
printf("%s\n", gt_str_array_get(seqids, i));
}
gt_str_array_delete(seqids);
}
gt_node_stream_delete(v_stream);
gt_node_stream_delete(in_stream);
gt_cstr_table_delete(cst);
return had_err;
}
static int gt_bed_to_gff3_runner(GT_UNUSED int argc, const char **argv,
int parsed_args, void *tool_arguments,
GtError *err)
{
GtNodeStream *bed_in_stream = NULL, *gff3_out_stream = NULL;
BEDToGFF3Arguments *arguments = tool_arguments;
int had_err;
gt_error_check(err);
/* create a BED input stream */
bed_in_stream = gt_bed_in_stream_new(argv[parsed_args]);
gt_bed_in_stream_set_feature_type((GtBEDInStream*) bed_in_stream,
gt_str_get(arguments->feature_type));
gt_bed_in_stream_set_thick_feature_type((GtBEDInStream*) bed_in_stream,
gt_str_get(arguments
->thick_feature_type));
gt_bed_in_stream_set_block_type((GtBEDInStream*) bed_in_stream,
gt_str_get(arguments->block_type));
/* create a GFF3 output stream */
/* XXX: use proper genfile */
gff3_out_stream = gt_gff3_out_stream_new(bed_in_stream, NULL);
/* pull the features through the stream and free them afterwards */
had_err = gt_node_stream_pull(gff3_out_stream, err);
/* free */
gt_node_stream_delete(gff3_out_stream);
gt_node_stream_delete(bed_in_stream);
return had_err;
}
static void infer_cds_visitor_test_data(GtQueue *queue)
{
GtError *error = gt_error_new();
const char *file = "data/gff3/grape-codons.gff3";
GtNodeStream *gff3in = gt_gff3_in_stream_new_unsorted(1, &file);
gt_gff3_in_stream_check_id_attributes((GtGFF3InStream *)gff3in);
gt_gff3_in_stream_enable_tidy_mode((GtGFF3InStream *)gff3in);
GtLogger *logger = gt_logger_new(true, "", stderr);
GtNodeStream *icv_stream = agn_infer_cds_stream_new(gff3in, NULL, logger);
GtArray *feats = gt_array_new( sizeof(GtFeatureNode *) );
GtNodeStream *arraystream = gt_array_out_stream_new(icv_stream, feats, error);
int pullresult = gt_node_stream_pull(arraystream, error);
if(pullresult == -1)
{
fprintf(stderr, "[AgnInferCDSVisitor::infer_cds_visitor_test_data] error "
"processing features: %s\n", gt_error_get(error));
}
gt_node_stream_delete(gff3in);
gt_node_stream_delete(icv_stream);
gt_node_stream_delete(arraystream);
gt_logger_delete(logger);
gt_array_sort(feats, (GtCompare)agn_genome_node_compare);
gt_array_reverse(feats);
while(gt_array_size(feats) > 0)
{
GtFeatureNode *fn = *(GtFeatureNode **)gt_array_pop(feats);
gt_queue_add(queue, fn);
}
gt_array_delete(feats);
gt_error_delete(error);
}
static int gt_mergefeat_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
InterFeatArguments *arguments = tool_arguments;
GtNodeStream *gff3_in_stream,
*merge_feature_stream,
*gff3_out_stream;
int had_err;
gt_error_check(err);
gt_assert(arguments);
/* create a gff3 input stream */
gff3_in_stream = gt_gff3_in_stream_new_unsorted(argc - parsed_args,
argv + parsed_args);
/* create merge feature stream */
merge_feature_stream = gt_merge_feature_stream_new(gff3_in_stream);
/* create gff3 output stream */
gff3_out_stream = gt_gff3_out_stream_new(merge_feature_stream,
arguments->outfp);
/* pull the features through the stream and free them afterwards */
had_err = gt_node_stream_pull(gff3_out_stream, err);
/* free */
gt_node_stream_delete(gff3_out_stream);
gt_node_stream_delete(merge_feature_stream);
gt_node_stream_delete(gff3_in_stream);
return had_err;
}
static int gt_csa_runner(GT_UNUSED int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
GtNodeStream *gff3_in_stream, *csa_stream, *gff3_out_stream;
CSAArguments *arguments = tool_arguments;
int had_err;
gt_error_check(err);
gt_assert(arguments);
/* create the streams */
gff3_in_stream = gt_gff3_in_stream_new_sorted(argv[parsed_args]);
if (arguments->verbose && arguments->outfp)
gt_gff3_in_stream_show_progress_bar((GtGFF3InStream*) gff3_in_stream);
csa_stream = gt_csa_stream_new(gff3_in_stream, arguments->join_length);
gff3_out_stream = gt_gff3_out_stream_new(csa_stream, arguments->outfp);
/* pull the features through the stream and free them afterwards */
had_err = gt_node_stream_pull(gff3_out_stream, err);
/* free */
gt_node_stream_delete(gff3_out_stream);
gt_node_stream_delete(csa_stream);
gt_node_stream_delete(gff3_in_stream);
return had_err;
}
static int gt_splicesiteinfo_runner(int argc, const char **argv,
int parsed_args, void *tool_arguments,
GtError *err)
{
SpliceSiteInfoArguments *arguments = tool_arguments;
GtNodeStream *gff3_in_stream = NULL,
*add_introns_stream = NULL,
*splice_site_info_stream = NULL;
GtRegionMapping *region_mapping;
int had_err = 0;
gt_error_check(err);
gt_assert(arguments);
if (!had_err) {
/* create gff3 input stream */
gff3_in_stream = gt_gff3_in_stream_new_unsorted(argc - parsed_args,
argv + parsed_args);
/* create region mapping */
region_mapping = gt_seqid2file_region_mapping_new(arguments->s2fi, err);
if (!region_mapping)
had_err = -1;
}
if (!had_err) {
/* create addintrons stream (if necessary) */
if (arguments->addintrons)
add_introns_stream = gt_add_introns_stream_new(gff3_in_stream);
/* create extract feature stream */
splice_site_info_stream = gt_splice_site_info_stream_new(
arguments->addintrons
? add_introns_stream
: gff3_in_stream,
region_mapping);
/* pull the features through the stream and free them afterwards */
had_err = gt_node_stream_pull(splice_site_info_stream, err);
}
if (!had_err) {
if (!gt_splice_site_info_stream_show(splice_site_info_stream,
arguments->outfp)) {
gt_warning("input file(s) contained no intron, use option -addintrons to "
"add introns automatically");
}
}
/* free */
gt_node_stream_delete(splice_site_info_stream);
gt_node_stream_delete(add_introns_stream);
gt_node_stream_delete(gff3_in_stream);
return had_err;
}
static void gv_test_calc_integrity(AgnUnitTest *test)
{
const char *filename = "data/gff3/gaeval-stream-unit-test-2.gff3";
GtNodeStream *align_in = gt_gff3_in_stream_new_unsorted(1, &filename);
AgnGaevalParams params = { 0.6, 0.3, 0.05, 0.05, 400, 200, 100 };
GtNodeVisitor *nv = agn_gaeval_visitor_new(align_in, params);
AgnGaevalVisitor *gv = gaeval_visitor_cast(nv);
gt_node_stream_delete(align_in);
GtNodeStream *gff3in = gt_gff3_in_stream_new_unsorted(1, &filename);
GtHashmap *typestokeep = gt_hashmap_new(GT_HASH_STRING, NULL, NULL);
gt_hashmap_add(typestokeep, "mRNA", "mRNA");
GtNodeStream *filtstream = agn_filter_stream_new(gff3in, typestokeep);
GtLogger *logger = gt_logger_new(true, "", stderr);
GtNodeStream *ics = agn_infer_cds_stream_new(filtstream, NULL, logger);
GtNodeStream *ies = agn_infer_exons_stream_new(ics, NULL, logger);
GtError *error = gt_error_new();
GtArray *feats = gt_array_new( sizeof(GtFeatureNode *) );
GtNodeStream *featstream = gt_array_out_stream_new(ies, feats, error);
int result = gt_node_stream_pull(featstream, error);
if(result == -1)
{
fprintf(stderr, "[AgnGaevalVisitor::gv_test_calc_integrity] error "
"processing GFF3: %s\n", gt_error_get(error));
return;
}
gt_node_stream_delete(gff3in);
gt_node_stream_delete(filtstream);
gt_node_stream_delete(featstream);
gt_node_stream_delete(ics);
gt_node_stream_delete(ies);
gt_logger_delete(logger);
gt_hashmap_delete(typestokeep);
agn_assert(gt_array_size(feats) == 2);
GtFeatureNode *g1 = *(GtFeatureNode **)gt_array_get(feats, 0);
GtFeatureNode *g2 = *(GtFeatureNode **)gt_array_get(feats, 1);
double cov1 = gaeval_visitor_calculate_coverage(gv, g1, error);
double cov2 = gaeval_visitor_calculate_coverage(gv, g2, error);
double int1 = gaeval_visitor_calculate_integrity(gv, g1, cov1, NULL, error);
double int2 = gaeval_visitor_calculate_integrity(gv, g2, cov2, NULL, error);
bool test1 = fabs(cov1 - 1.000) < 0.001 &&
fabs(cov2 - 0.997) < 0.001 &&
fabs(int1 - 0.850) < 0.001 &&
fabs(int2 - 0.863) < 0.001;
agn_unit_test_result(test, "calculate integrity", test1);
gt_error_delete(error);
gt_array_delete(feats);
gt_genome_node_delete((GtGenomeNode *)g1);
gt_genome_node_delete((GtGenomeNode *)g2);
gt_node_visitor_delete(nv);
}
static int gt_inlineseq_split_runner(int argc, const char **argv,
int parsed_args,
void *tool_arguments, GtError *err)
{
GtInlineseqSplitArguments *arguments = tool_arguments;
GtNodeStream *gff3_in_stream = NULL,
*gff3_out_stream = NULL,
*split_stream = NULL,
*last_stream = NULL;
GtFile *seq_out_file = NULL,
*gff3_out_file = NULL;
int had_err = 0;
gt_error_check(err);
gt_assert(arguments);
if (gt_str_length(arguments->seqoutfile) > 0) {
seq_out_file = gt_file_new(gt_str_get(arguments->seqoutfile), "w+", err);
if (!seq_out_file)
had_err = -1;
}
if (!had_err && gt_str_length(arguments->gffoutfile) > 0) {
gff3_out_file = gt_file_new(gt_str_get(arguments->gffoutfile), "w+", err);
if (!gff3_out_file)
had_err = -1;
}
if (!had_err) {
last_stream = gff3_in_stream = gt_gff3_in_stream_new_unsorted(
argc - parsed_args,
argv + parsed_args);
gt_assert(gff3_in_stream);
}
if (!had_err) {
last_stream = split_stream = gt_sequence_node_out_stream_new(last_stream,
seq_out_file,
err);
gt_assert(split_stream);
}
if (!had_err) {
last_stream = gff3_out_stream = gt_gff3_out_stream_new(last_stream,
gff3_out_file);
had_err = gt_node_stream_pull(last_stream, err);
}
gt_node_stream_delete(gff3_in_stream);
gt_node_stream_delete(gff3_out_stream);
gt_node_stream_delete(split_stream);
gt_file_delete(seq_out_file);
gt_file_delete(gff3_out_file);
return had_err;
}
static int gt_gff3validator_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
GFF3ValidatorArguments *arguments = tool_arguments;
GtTypeChecker *type_checker = NULL;
GtXRFChecker *xrf_checker = NULL;
GtNodeStream *gff3_in_stream;
int had_err = 0;
gt_error_check(err);
gt_assert(arguments);
/* create a GFF3 input stream */
gff3_in_stream = gt_gff3_in_stream_new_unsorted(argc - parsed_args,
argv + parsed_args);
gt_gff3_in_stream_check_id_attributes((GtGFF3InStream*) gff3_in_stream);
/* set different type checker if necessary */
if (gt_typecheck_info_option_used(arguments->tci)) {
type_checker = gt_typecheck_info_create_type_checker(arguments->tci, err);
if (!type_checker)
had_err = -1;
if (!had_err)
gt_gff3_in_stream_set_type_checker(gff3_in_stream, type_checker);
}
/* set XRF checker */
if (gt_xrfcheck_info_option_used(arguments->xci)) {
xrf_checker = gt_xrfcheck_info_create_xrf_checker(arguments->xci, err);
if (!xrf_checker)
had_err = -1;
if (!had_err)
gt_gff3_in_stream_set_xrf_checker(gff3_in_stream, xrf_checker);
}
/* enable strict mode (if necessary) */
if (!had_err && arguments->strict)
gt_gff3_in_stream_enable_strict_mode((GtGFF3InStream*) gff3_in_stream);
/* pull the features through the stream and free them afterwards */
if (!had_err)
had_err = gt_node_stream_pull(gff3_in_stream, err);
if (!had_err)
printf("input is valid GFF3\n");
/* free */
gt_node_stream_delete(gff3_in_stream);
gt_type_checker_delete(type_checker);
gt_xrf_checker_delete(xrf_checker);
return had_err;
}
static int gt_tir_runner(GT_UNUSED int argc, GT_UNUSED const char **argv,
GT_UNUSED int parsed_args, void *tool_arguments,
GtError *err)
{
GtTirArguments *arguments = tool_arguments;
GtNodeStream *tir_stream = NULL,
*gff3_out_stream = NULL,
*last_stream = NULL;
int had_err = 0;
gt_error_check(err);
gt_assert(arguments);
tir_stream = gt_tir_stream_new(arguments->str_indexname,
arguments->min_seed_length,
arguments->min_TIR_length,
arguments->max_TIR_length,
arguments->min_TIR_distance,
arguments->max_TIR_distance,
arguments->arbit_scores,
arguments->xdrop_belowscore,
arguments->similarity_threshold,
arguments->best_overlaps,
arguments->no_overlaps,
arguments->min_TSD_length,
arguments->max_TSD_length,
arguments->vicinity,
err);
if (tir_stream == NULL)
return -1;
last_stream = tir_stream;
/* gff3 outstream */
gff3_out_stream = gt_gff3_out_stream_new(last_stream, NULL);
last_stream = gff3_out_stream;
/* output arguments line */
/* gt_tir_showargsline(argc, argv); */
/* pull the features through the stream and free them afterwards */
if (!had_err)
had_err = gt_node_stream_pull(last_stream, err);
/* free */
gt_node_stream_delete(tir_stream);
gt_node_stream_delete(gff3_out_stream);
return had_err;
}
int gt_chseqids(int argc, const char **argv, GtError *err)
{
GtNodeStream *gff3_in_stream, *chseqids_stream, *sort_stream = NULL,
*gff3_out_stream = NULL;
ChseqidsArguments arguments;
GtStr *chseqids;
int parsed_args, had_err = 0;
gt_error_check(err);
/* option parsing */
switch (parse_options(&parsed_args, &arguments, argc, argv, err)) {
case GT_OPTION_PARSER_OK: break;
case GT_OPTION_PARSER_ERROR: return -1;
case GT_OPTION_PARSER_REQUESTS_EXIT: return 0;
}
/* create the streams */
gff3_in_stream = gt_gff3_in_stream_new_sorted(argv[parsed_args + 1]);
if (arguments.verbose && arguments.outfp)
gt_gff3_in_stream_show_progress_bar((GtGFF3InStream*) gff3_in_stream);
chseqids = gt_str_new_cstr(argv[parsed_args]);
chseqids_stream = gt_chseqids_stream_new(gff3_in_stream, chseqids, err);
if (!chseqids_stream)
had_err = -1;
gt_str_delete(chseqids);
if (!had_err) {
if (arguments.sort) {
sort_stream = gt_sort_stream_new(chseqids_stream);
gff3_out_stream = gt_gff3_out_stream_new(sort_stream, arguments.outfp);
}
else {
gff3_out_stream = gt_gff3_out_stream_new(chseqids_stream,
arguments.outfp);
}
}
/* pull the features through the stream and free them afterwards */
if (!had_err)
had_err = gt_node_stream_pull(gff3_out_stream, err);
/* free */
gt_node_stream_delete(gff3_out_stream);
gt_node_stream_delete(chseqids_stream);
gt_node_stream_delete(sort_stream);
gt_node_stream_delete(gff3_in_stream);
gt_file_delete(arguments.outfp);
return had_err;
}
static int gt_inlineseq_add_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
GtNodeStream *gff3_in_stream = NULL,
*add_stream = NULL,
*gff3_out_stream = NULL,
*last_stream = NULL;
GtRegionMapping *rm = NULL;
InlineseqAddArguments *arguments = tool_arguments;
int had_err = 0;
gt_error_check(err);
/* add region mapping if given */
if (gt_seqid2file_option_used(arguments->s2fi)) {
rm = gt_seqid2file_region_mapping_new(arguments->s2fi, err);
if (!rm)
had_err = -1;
}
if (!had_err) {
last_stream = gff3_in_stream = gt_gff3_in_stream_new_unsorted(
argc - parsed_args,
argv + parsed_args);
gt_assert(gff3_in_stream);
gt_gff3_in_stream_enable_tidy_mode((GtGFF3InStream*) gff3_in_stream);
last_stream = add_stream = gt_sequence_node_add_stream_new(last_stream, rm,
err);
if (!add_stream) {
had_err = -1;
}
}
if (!had_err) {
last_stream = gff3_out_stream = gt_gff3_out_stream_new(last_stream,
arguments->outfp);
}
if (!had_err)
had_err = gt_node_stream_pull(last_stream, err);
/* free */
gt_node_stream_delete(gff3_in_stream);
gt_node_stream_delete(add_stream);
gt_node_stream_delete(gff3_out_stream);
gt_region_mapping_delete(rm);
return had_err;
}
static int gt_extractfeat_runner(GT_UNUSED int argc, const char **argv,
int parsed_args, void *tool_arguments,
GtError *err)
{
GtNodeStream *gff3_in_stream = NULL, *extract_feature_stream = NULL;
GtExtractFeatArguments *arguments = tool_arguments;
GtRegionMapping *region_mapping;
int had_err = 0;
gt_error_check(err);
gt_assert(arguments);
if (!had_err) {
/* create gff3 input stream */
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 mapping */
region_mapping = gt_seqid2file_region_mapping_new(arguments->s2fi, err);
if (!region_mapping)
had_err = -1;
}
if (!had_err) {
/* create extract feature stream */
extract_feature_stream =
gt_extract_feature_stream_new(gff3_in_stream,
region_mapping,
gt_str_get(arguments->type),
arguments->join,
arguments->translate,
arguments->seqid,
arguments->target,
arguments->width,
arguments->outfp);
/* pull the features through the stream and free them afterwards */
had_err = gt_node_stream_pull(extract_feature_stream, err);
}
/* free */
gt_node_stream_delete(extract_feature_stream);
gt_node_stream_delete(gff3_in_stream);
return had_err;
}
static int gt_cds_runner(GT_UNUSED int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
GtNodeStream *gff3_in_stream, *cds_stream = NULL, *gff3_out_stream = NULL;
CDSArguments *arguments = tool_arguments;
GtRegionMapping *region_mapping;
int had_err = 0;
gt_error_check(err);
gt_assert(arguments);
/* create gff3 input stream */
gff3_in_stream = gt_gff3_in_stream_new_sorted(argv[parsed_args]);
if (arguments->verbose && arguments->outfp)
gt_gff3_in_stream_show_progress_bar((GtGFF3InStream*) gff3_in_stream);
/* create region mapping */
region_mapping = gt_seqid2file_region_mapping_new(arguments->s2fi, err);
if (!region_mapping)
had_err = -1;
if (!had_err) {
/* create CDS stream */
cds_stream = gt_cds_stream_new(gff3_in_stream, region_mapping,
arguments->minorflen, GT_CDS_SOURCE_TAG,
arguments->start_codon,
arguments->final_stop_codon,
arguments->generic_start_codons);
/* create gff3 output stream */
gff3_out_stream = gt_gff3_out_stream_new(cds_stream, arguments->outfp);
/* pull the features through the stream and free them afterwards */
had_err = gt_node_stream_pull(gff3_out_stream, err);
}
/* free */
gt_node_stream_delete(gff3_out_stream);
gt_node_stream_delete(cds_stream);
gt_node_stream_delete(gff3_in_stream);
return had_err;
}
static void gv_test_intersect(AgnUnitTest *test)
{
GtArray *feats = gt_array_new( sizeof(GtFeatureNode *) );
GtError *error = gt_error_new();
const char *filename = "data/gff3/gaeval-stream-unit-test-1.gff3";
GtNodeStream *gff3in = gt_gff3_in_stream_new_unsorted(1, &filename);
GtNodeStream *fstream = gt_array_out_stream_new(gff3in, feats, error);
int result = gt_node_stream_pull(fstream, error);
if(result == -1)
{
fprintf(stderr, "[AgnGaevalVisitor::gv_test_intersect] error "
"processing GFF3: %s\n", gt_error_get(error));
return;
}
gt_error_delete(error);
gt_node_stream_delete(gff3in);
gt_node_stream_delete(fstream);
agn_assert(gt_array_size(feats) == 9);
GtGenomeNode *g1 = *(GtGenomeNode **)gt_array_get(feats, 1);
GtGenomeNode *g2 = *(GtGenomeNode **)gt_array_get(feats, 3);
GtGenomeNode *g3 = *(GtGenomeNode **)gt_array_get(feats, 7);
GtGenomeNode *est1 = *(GtGenomeNode **)gt_array_get(feats, 0);
GtGenomeNode *est2 = *(GtGenomeNode **)gt_array_get(feats, 2);
GtGenomeNode *est3 = *(GtGenomeNode **)gt_array_get(feats, 4);
GtGenomeNode *est4 = *(GtGenomeNode **)gt_array_get(feats, 5);
GtGenomeNode *est5 = *(GtGenomeNode **)gt_array_get(feats, 6);
GtGenomeNode *est6 = *(GtGenomeNode **)gt_array_get(feats, 8);
GtArray *cov = gaeval_visitor_intersect(g1, est1);
bool test1 = cov == NULL;
cov = gaeval_visitor_intersect(g1, est2);
test1 = gt_array_size(cov) == 1;
if(test1)
{
GtRange *range01 = gt_array_pop(cov);
GtRange testrange = { 400, 500 };
test1 = gt_range_compare(range01, &testrange) == 0;
}
agn_unit_test_result(test, "intersect (1)", test1);
gt_array_delete(cov);
cov = gaeval_visitor_intersect(g2, est3);
bool test2 = gt_array_size(cov) == 2;
if(test2)
{
GtRange *range01 = gt_array_get(cov, 0);
GtRange *range02 = gt_array_get(cov, 1);
GtRange testrange1 = { 800, 900 };
GtRange testrange2 = { 1050, 1075 };
test2 = gt_range_compare(range01, &testrange1) == 0 &&
gt_range_compare(range02, &testrange2) == 0;
}
agn_unit_test_result(test, "intersect (2)", test2);
gt_array_delete(cov);
cov = gaeval_visitor_intersect(g2, est4);
bool test3 = gt_array_size(cov) == 2;
if(test3)
{
GtRange *range01 = gt_array_get(cov, 0);
GtRange *range02 = gt_array_get(cov, 1);
GtRange testrange1 = { 1070, 1125 };
GtRange testrange2 = { 1250, 1310 };
test3 = gt_range_compare(range01, &testrange1) == 0 &&
gt_range_compare(range02, &testrange2) == 0;
}
agn_unit_test_result(test, "intersect (3)", test3);
gt_array_delete(cov);
cov = gaeval_visitor_intersect(g3, est5);
bool test4 = gt_array_size(cov) == 2;
if(test4)
{
GtRange *range01 = gt_array_get(cov, 0);
GtRange *range02 = gt_array_get(cov, 1);
GtRange testrange1 = { 2000, 3000 };
GtRange testrange2 = { 4000, 5000 };
test4 = gt_range_compare(range01, &testrange1) == 0 &&
gt_range_compare(range02, &testrange2) == 0;
}
agn_unit_test_result(test, "intersect (4)", test4);
gt_array_delete(cov);
cov = gaeval_visitor_intersect(g3, est6);
bool test5 = gt_array_size(cov) == 2;
if(test5)
{
GtRange *range01 = gt_array_get(cov, 0);
GtRange *range02 = gt_array_get(cov, 1);
GtRange testrange1 = { 2500, 3000 };
GtRange testrange2 = { 4000, 5000 };
test5 = gt_range_compare(range01, &testrange1) == 0 &&
gt_range_compare(range02, &testrange2) == 0;
}
agn_unit_test_result(test, "intersect (5)", test5);
gt_array_delete(cov);
gt_array_delete(feats);
gt_genome_node_delete(g1);
gt_genome_node_delete(g2);
gt_genome_node_delete(g3);
gt_genome_node_delete(est1);
gt_genome_node_delete(est2);
gt_genome_node_delete(est3);
gt_genome_node_delete(est4);
gt_genome_node_delete(est5);
gt_genome_node_delete(est6);
}
static int gt_speck_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
GtNodeStream *gff3_in_stream = NULL, *checker_stream = NULL,
*a_in_stream = NULL, *a_out_stream = NULL,
*feature_stream = NULL, *sort_stream = NULL,
*last_stream = NULL;
GtNodeVisitor *spec_visitor = NULL;
GtSpecResults *res = NULL;
GtFeatureIndex *fi = NULL;
GtTimer *t = NULL;
GtRegionMapping *rm = NULL;
GtArray *arr = gt_array_new(sizeof (GtFeatureNode*));
SpeccheckArguments *arguments = tool_arguments;
int had_err = 0;
gt_error_check(err);
res = gt_spec_results_new();
gt_assert(res);
t = gt_timer_new();
gt_assert(t);
spec_visitor = gt_spec_visitor_new(gt_str_get(arguments->specfile), res,
err);
if (!spec_visitor)
return -1;
/* add region mapping if given */
if (gt_seqid2file_option_used(arguments->s2fi)) {
rm = gt_seqid2file_region_mapping_new(arguments->s2fi, err);
if (!rm)
had_err = -1;
if (!had_err)
gt_spec_visitor_add_region_mapping((GtSpecVisitor*) spec_visitor, rm);
}
/* set runtime error behaviour */
if (arguments->fail_hard)
gt_spec_visitor_fail_on_runtime_error((GtSpecVisitor*) spec_visitor);
else
gt_spec_visitor_report_runtime_errors((GtSpecVisitor*) spec_visitor);
/* redirect warnings */
gt_warning_set_handler(gt_speck_record_warning, res);
last_stream = gff3_in_stream = gt_gff3_in_stream_new_unsorted(
argc - parsed_args,
argv + parsed_args);
gt_assert(gff3_in_stream);
gt_gff3_in_stream_enable_tidy_mode((GtGFF3InStream*) gff3_in_stream);
/* insert sort stream if requested */
if (arguments->sort) {
last_stream = sort_stream = gt_sort_stream_new(last_stream);
}
/* if -provideindex is given, collect input features and index them first */
if (arguments->provideindex) {
fi = gt_feature_index_memory_new();
gt_assert(fi);
last_stream = feature_stream = gt_feature_stream_new(last_stream, fi);
gt_assert(feature_stream);
last_stream = a_out_stream = gt_array_out_stream_all_new(last_stream, arr,
err);
if (!a_out_stream)
had_err = -1;
gt_timer_start(t);
if (!had_err)
had_err = gt_node_stream_pull(last_stream, err);
if (!had_err) {
gt_spec_visitor_add_feature_index((GtSpecVisitor*) spec_visitor,
gt_feature_index_ref(fi));
last_stream = a_in_stream = gt_array_in_stream_new(arr, NULL, err);
if (!a_in_stream)
had_err = -1;
}
} else {
gt_timer_start(t);
}
if (!had_err) {
checker_stream = gt_visitor_stream_new(last_stream, spec_visitor);
gt_assert(checker_stream);
}
/* perform checking */
if (!had_err)
had_err = gt_node_stream_pull(checker_stream, err);
gt_timer_stop(t);
/* reset warnings output */
gt_warning_set_handler(gt_warning_default_handler, NULL);
/* output results */
if (!had_err)
gt_spec_results_report(res, arguments->outfp,
gt_str_get(arguments->specfile),
arguments->verbose, arguments->colored,
!arguments->allexpects);
if (!had_err)
gt_timer_show_formatted(t, "Finished in " GT_WD ".%06ld s.\n", stderr);
/* free */
gt_node_stream_delete(gff3_in_stream);
gt_node_stream_delete(a_in_stream);
gt_node_stream_delete(a_out_stream);
gt_node_stream_delete(checker_stream);
gt_node_stream_delete(feature_stream);
gt_node_stream_delete(sort_stream);
gt_spec_results_delete(res);
gt_feature_index_delete(fi);
gt_timer_delete(t);
gt_array_delete(arr);
return had_err;
}
GtNodeVisitor*
agn_gaeval_visitor_new(GtNodeStream *astream, AgnGaevalParams gparams)
{
agn_assert(astream);
// Create the node visitor
GtNodeVisitor *nv = gt_node_visitor_create(gaeval_visitor_class());
AgnGaevalVisitor *v = gaeval_visitor_cast(nv);
v->alignments = gt_feature_index_memory_new();
v->tsvout = NULL;
v->params = gparams;
// Check that sum of weights is 1.0
double weights_total = gparams.alpha + gparams.beta +
gparams.gamma + gparams.epsilon;
if(fabs(weights_total - 1.0) > 0.0001)
{
fprintf(stderr, "[AgnGaevalVisitor::agn_gaeval_visitor_new] warning: "
"sum of weights is not 1.0 %.3lf; integrity calculations will be "
"incorrect\n", weights_total);
}
// Set up node stream to load alignment features into memory
GtQueue *streams = gt_queue_new();
GtNodeStream *stream, *last_stream;
GtHashmap *typestokeep = gt_hashmap_new(GT_HASH_STRING, NULL, NULL);
gt_hashmap_add(typestokeep, "cDNA_match", "cDNA_match");
gt_hashmap_add(typestokeep, "EST_match", "EST_match");
gt_hashmap_add(typestokeep, "nucleotide_match", "nucleotide_match");
stream = agn_filter_stream_new(astream, typestokeep);
gt_queue_add(streams, stream);
last_stream = stream;
stream = gt_feature_out_stream_new(last_stream, v->alignments);
gt_queue_add(streams, stream);
last_stream = stream;
stream = gt_inter_feature_stream_new(last_stream, "cDNA_match", "match_gap");
gt_queue_add(streams, stream);
last_stream = stream;
stream = gt_inter_feature_stream_new(last_stream, "EST_match", "match_gap");
gt_queue_add(streams, stream);
last_stream = stream;
stream = gt_inter_feature_stream_new(last_stream, "nucleotide_match",
"match_gap");
gt_queue_add(streams, stream);
last_stream = stream;
// Process the node stream
GtError *error = gt_error_new();
int result = gt_node_stream_pull(last_stream, error);
if(result == -1)
{
fprintf(stderr, "[AEGeAn::AgnGaevalStream] error parsing alignments: %s\n",
gt_error_get(error));
gt_node_visitor_delete(nv);
return NULL;
}
gt_error_delete(error);
gt_hashmap_delete(typestokeep);
while(gt_queue_size(streams) > 0)
{
stream = gt_queue_get(streams);
gt_node_stream_delete(stream);
}
gt_queue_delete(streams);
return nv;
}
static int gt_select_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
SelectArguments *arguments = tool_arguments;
GtNodeStream *gff3_in_stream, *select_stream,
*targetbest_select_stream = NULL, *gff3_out_stream;
int had_err;
GtFile *drop_file = NULL;
GtNodeVisitor *gff3outvis = NULL;
gt_error_check(err);
gt_assert(arguments);
/* create a gff3 input stream */
gff3_in_stream = gt_gff3_in_stream_new_unsorted(argc - parsed_args,
argv + parsed_args);
if (arguments->verbose && arguments->outfp)
gt_gff3_in_stream_show_progress_bar((GtGFF3InStream*) gff3_in_stream);
/* create a filter stream */
select_stream = gt_select_stream_new(gff3_in_stream, arguments->seqid,
arguments->source,
&arguments->contain_range,
&arguments->overlap_range,
arguments->strand,
arguments->targetstrand,
arguments->has_CDS,
arguments->max_gene_length,
arguments->max_gene_num,
arguments->min_gene_score,
arguments->max_gene_score,
arguments->min_average_splice_site_prob,
arguments->feature_num,
arguments->filter_files,
arguments->filter_logic,
err);
if (select_stream) {
GtSelectStream *fs = (GtSelectStream*) select_stream;
if (gt_str_length(arguments->dropped_file) > 0) {
drop_file = gt_file_new(gt_str_get(arguments->dropped_file), "w", err);
gff3outvis = gt_gff3_visitor_new(drop_file);
gt_select_stream_set_drophandler(fs, print_to_file_drophandler,
(void*) gff3outvis);
} else {
gt_select_stream_set_drophandler(fs, default_drophandler, NULL);
}
gt_select_stream_set_single_intron_factor(select_stream,
arguments->single_intron_factor);
if (arguments->targetbest)
targetbest_select_stream = gt_targetbest_select_stream_new(select_stream);
/* create a gff3 output stream */
gff3_out_stream = gt_gff3_out_stream_new(arguments->targetbest
? targetbest_select_stream
: select_stream,
arguments->outfp);
/* pull the features through the stream and free them afterwards */
had_err = gt_node_stream_pull(gff3_out_stream, err);
/* free */
gt_node_stream_delete(gff3_out_stream);
gt_node_stream_delete(select_stream);
gt_node_stream_delete(targetbest_select_stream);
} else {
had_err = -1;
}
gt_file_delete(drop_file);
gt_node_visitor_delete(gff3outvis);
gt_node_stream_delete(gff3_in_stream);
return had_err;
}
static int gt_ltrdigest_runner(GT_UNUSED int argc, const char **argv,
int parsed_args, void *tool_arguments,
GtError *err)
{
GtLTRdigestOptions *arguments = tool_arguments;
GtNodeStream *gff3_in_stream = NULL,
*gff3_out_stream = NULL,
*ltrdigest_stream = NULL,
*tab_out_stream = NULL,
*last_stream = NULL;
int had_err = 0,
tests_to_run = 0,
arg = parsed_args;
const char *indexname = argv[arg+1];
GtLogger *logger = gt_logger_new(arguments->verbose,
GT_LOGGER_DEFLT_PREFIX, stdout);
GtEncseqLoader *el;
GtEncseq *encseq;
gt_error_check(err);
gt_assert(arguments);
/* Set sequence encoder options. Defaults are ok. */
el = gt_encseq_loader_new();
gt_encseq_loader_set_logger(el, logger);
/* Open sequence file */
encseq = gt_encseq_loader_load(el, indexname, err);
if (!encseq)
had_err = -1;
/* Always search for PPT. */
tests_to_run |= GT_LTRDIGEST_RUN_PPT;
/* Open tRNA library if given. */
if (!had_err && arguments->trna_lib
&& gt_str_length(arguments->trna_lib) > 0)
{
tests_to_run |= GT_LTRDIGEST_RUN_PBS;
arguments->pbs_opts.trna_lib = gt_bioseq_new(gt_str_get(arguments->trna_lib),
err);
if (gt_error_is_set(err))
had_err = -1;
}
#ifdef HAVE_HMMER
/* Open HMMER files if given. */
if (!had_err && gt_str_array_size(arguments->pdom_opts.hmm_files) > 0)
{
tests_to_run |= GT_LTRDIGEST_RUN_PDOM;
if (!strcmp(gt_str_get(arguments->cutoffs), "GA")) {
arguments->pdom_opts.cutoff = GT_PHMM_CUTOFF_GA;
} else if (!strcmp(gt_str_get(arguments->cutoffs), "TC")) {
arguments->pdom_opts.cutoff = GT_PHMM_CUTOFF_TC;
} else if (!strcmp(gt_str_get(arguments->cutoffs), "NONE")) {
arguments->pdom_opts.cutoff = GT_PHMM_CUTOFF_NONE;
} else {
gt_error_set(err, "invalid cutoff setting!");
had_err = -1;
}
}
#endif
if (!had_err)
{
/* set up stream flow
* ------------------*/
last_stream = gff3_in_stream = gt_gff3_in_stream_new_sorted(argv[arg]);
last_stream = ltrdigest_stream = gt_ltrdigest_stream_new(last_stream,
tests_to_run,
encseq,
&arguments->pbs_opts,
&arguments->ppt_opts,
#ifdef HAVE_HMMER
&arguments->pdom_opts,
#endif
err);
if (!ltrdigest_stream)
had_err = -1;
}
if (!had_err)
{
/* attach tabular output stream, if requested */
if (gt_str_length(arguments->prefix) > 0)
{
last_stream = tab_out_stream = gt_ltr_fileout_stream_new(last_stream,
tests_to_run,
encseq,
gt_str_get(arguments->prefix),
&arguments->ppt_opts,
&arguments->pbs_opts,
#ifdef HAVE_HMMER
&arguments->pdom_opts,
#endif
gt_str_get(arguments->trna_lib),
argv[arg+1],
argv[arg],
arguments->seqnamelen,
err);
#ifdef HAVE_HMMER
if (&arguments->pdom_opts.write_alignments)
gt_ltr_fileout_stream_enable_pdom_alignment_output(tab_out_stream);
if (&arguments->pdom_opts.write_aaseqs)
gt_ltr_fileout_stream_enable_aa_sequence_output(tab_out_stream);
#endif
}
last_stream = gff3_out_stream = gt_gff3_out_stream_new(last_stream,
arguments->outfp);
/* pull the features through the stream and free them afterwards */
had_err = gt_node_stream_pull(last_stream, err);
}
gt_node_stream_delete(gff3_out_stream);
gt_node_stream_delete(ltrdigest_stream);
if (tab_out_stream != NULL)
gt_node_stream_delete(tab_out_stream);
gt_node_stream_delete(gff3_in_stream);
gt_encseq_loader_delete(el);
gt_encseq_delete(encseq);
encseq = NULL;
gt_bioseq_delete(arguments->pbs_opts.trna_lib);
gt_logger_delete(logger);
return had_err;
}
int gt_feature_in_stream_unit_test(GtError *error)
{
GtNodeStream *src, *dest;
GtFeatureIndex *prefeat, *postfeat;
GtRange range1, range1test, range2, range2test;
prefeat = in_stream_test_data(error);
postfeat = gt_feature_index_memory_new();
src = gt_feature_in_stream_new(prefeat);
dest = gt_feature_out_stream_new(src, postfeat);
int result = gt_node_stream_pull(dest, error);
if (result == -1)
return -1;
GtStrArray *seqids = gt_feature_index_get_seqids(postfeat, error);
if (gt_str_array_size(seqids) != 2)
{
gt_error_set(error, "error in feature_in_stream unit test 1: expected 2 "
"seqids, found "GT_WU"", gt_str_array_size(seqids));
return -1;
}
gt_str_array_delete(seqids);
range1test.start = 500; range1test.end = 75000;
range2test.start = 4000; range2test.end = 9500;
gt_feature_index_get_range_for_seqid(postfeat, &range1, "chr1", error);
gt_feature_index_get_range_for_seqid(postfeat, &range2, "scf0001",error);
if (gt_range_compare(&range1, &range1test) ||
gt_range_compare(&range2, &range2test))
{
gt_error_set(error, "error in feature_in_stream unit test 1: incorrect "
"sequence regions");
return -1;
}
gt_feature_index_get_orig_range_for_seqid(postfeat, &range1, "chr1", error);
gt_feature_index_get_orig_range_for_seqid(postfeat, &range2, "scf0001",error);
if (gt_range_compare(&range1, &range1test) ||
gt_range_compare(&range2, &range2test))
{
gt_error_set(error, "error in feature_in_stream unit test 1: incorrect "
"sequence regions");
return -1;
}
gt_feature_index_delete(prefeat);
gt_feature_index_delete(postfeat);
gt_node_stream_delete(src);
gt_node_stream_delete(dest);
prefeat = in_stream_test_data(error);
postfeat = gt_feature_index_memory_new();
src = gt_feature_in_stream_new(prefeat);
dest = gt_feature_out_stream_new(src, postfeat);
gt_feature_in_stream_use_orig_ranges((GtFeatureInStream *)src);
result = gt_node_stream_pull(dest, error);
if (result == -1)
return -1;
range1test.start = 500; range1test.end = 75000;
range2test.start = 4000; range2test.end = 9500;
gt_feature_index_get_range_for_seqid(postfeat, &range1, "chr1", error);
gt_feature_index_get_range_for_seqid(postfeat, &range2, "scf0001",error);
if (gt_range_compare(&range1, &range1test) ||
gt_range_compare(&range2, &range2test))
{
gt_error_set(error, "error in feature_in_stream unit test 1: incorrect "
"sequence regions");
return -1;
}
range1test.start = 1; range1test.end = 100000;
range2test.start = 1; range2test.end = 10000;
gt_feature_index_get_orig_range_for_seqid(postfeat, &range1, "chr1", error);
gt_feature_index_get_orig_range_for_seqid(postfeat, &range2, "scf0001",error);
if (gt_range_compare(&range1, &range1test) ||
gt_range_compare(&range2, &range2test))
{
gt_error_set(error, "error in feature_in_stream unit test 1: incorrect "
"sequence regions");
return -1;
}
gt_feature_index_delete(prefeat);
gt_feature_index_delete(postfeat);
gt_node_stream_delete(src);
gt_node_stream_delete(dest);
return 0;
}
static int gt_speck_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
GtNodeStream *gff3_in_stream = NULL, *checker_stream = NULL,
*a_in_stream = NULL, *a_out_stream = NULL,
*feature_stream = NULL, *sort_stream = NULL,
*last_stream = NULL;
GtNodeVisitor *spec_visitor = NULL;
GtSpecResults *res = NULL;
GtFeatureIndex *fi = NULL;
GtTypeChecker *type_checker = NULL;
GtTimer *t = NULL;
GtRegionMapping *rm = NULL;
GtArray *arr = gt_array_new(sizeof (GtFeatureNode*));
GtStr *prog, *speclib;
SpeccheckArguments *arguments = tool_arguments;
int had_err = 0;
gt_error_check(err);
res = gt_spec_results_new();
gt_assert(res);
if (gt_file_exists(gt_str_get(arguments->format))) {
speclib = gt_str_ref(arguments->format);
} else {
prog = gt_str_new();
gt_str_append_cstr_nt(prog, gt_error_get_progname(err),
gt_cstr_length_up_to_char(gt_error_get_progname(err), ' '));
speclib = gt_get_gtdata_path(gt_str_get(prog), NULL);
gt_str_delete(prog);
gt_str_append_cstr(speclib, "/spec/output_drivers/");
gt_str_append_str(speclib, arguments->format);
if (!gt_file_exists(gt_str_get(speclib))) {
gt_error_set(err, "output driver file \"%s\" does not exist",
gt_str_get(speclib));
had_err = -1;
}
}
if (!had_err) {
spec_visitor = gt_spec_visitor_new(gt_str_get(arguments->specfile), res,
err);
if (!spec_visitor) {
gt_spec_results_delete(res);
return -1;
}
}
t = gt_timer_new();
gt_assert(t);
/* add region mapping if given */
if (!had_err && gt_seqid2file_option_used(arguments->s2fi)) {
rm = gt_seqid2file_region_mapping_new(arguments->s2fi, err);
if (!rm)
had_err = -1;
if (!had_err)
gt_spec_visitor_add_region_mapping((GtSpecVisitor*) spec_visitor, rm);
}
/* set type checker if necessary */
if (!had_err && gt_typecheck_info_option_used(arguments->tci)) {
type_checker = gt_typecheck_info_create_type_checker(arguments->tci, err);
if (!type_checker)
had_err = -1;
if (!had_err)
gt_spec_visitor_add_type_checker((GtSpecVisitor*) spec_visitor,
type_checker);
}
if (!had_err) {
/* set runtime error behaviour */
if (arguments->fail_hard)
gt_spec_visitor_fail_on_runtime_error((GtSpecVisitor*) spec_visitor);
else
gt_spec_visitor_report_runtime_errors((GtSpecVisitor*) spec_visitor);
/* redirect warnings */
gt_warning_set_handler(gt_speck_record_warning, res);
last_stream = gff3_in_stream = gt_gff3_in_stream_new_unsorted(
argc - parsed_args,
argv + parsed_args);
gt_assert(gff3_in_stream);
gt_gff3_in_stream_enable_tidy_mode((GtGFF3InStream*) gff3_in_stream);
/* insert sort stream if requested */
if (arguments->sort) {
last_stream = sort_stream = gt_sort_stream_new(last_stream);
}
/* if -provideindex is given, collect input features and index them first */
if (arguments->provideindex) {
fi = gt_feature_index_memory_new();
gt_assert(fi);
last_stream = feature_stream = gt_feature_stream_new(last_stream, fi);
gt_assert(feature_stream);
last_stream = a_out_stream = gt_array_out_stream_all_new(last_stream, arr,
err);
if (!a_out_stream)
had_err = -1;
gt_timer_start(t);
if (!had_err)
had_err = gt_node_stream_pull(last_stream, err);
if (!had_err) {
gt_spec_visitor_add_feature_index((GtSpecVisitor*) spec_visitor,
gt_feature_index_ref(fi));
last_stream = a_in_stream = gt_array_in_stream_new(arr, NULL, err);
if (!a_in_stream)
had_err = -1;
}
} else {
gt_timer_start(t);
}
if (!had_err) {
checker_stream = gt_visitor_stream_new(last_stream, spec_visitor);
gt_assert(checker_stream);
}
/* perform checking */
if (!had_err)
had_err = gt_node_stream_pull(checker_stream, err);
gt_timer_stop(t);
/* reset warnings output */
gt_warning_set_handler(gt_warning_default_handler, NULL);
/* output results */
if (!had_err) {
GtStr *runtime = gt_str_new();
gt_timer_get_formatted(t, GT_WD ".%06ld", runtime);
had_err = gt_spec_results_render_template(res, gt_str_get(speclib),
arguments->outfp,
gt_str_get(arguments->specfile),
arguments->verbose,
arguments->colored,
gt_str_get(runtime), err);
gt_str_delete(runtime);
}
}
/* free */
gt_node_stream_delete(gff3_in_stream);
gt_node_stream_delete(a_in_stream);
gt_node_stream_delete(a_out_stream);
gt_node_stream_delete(checker_stream);
gt_node_stream_delete(feature_stream);
gt_node_stream_delete(sort_stream);
gt_spec_results_delete(res);
gt_feature_index_delete(fi);
gt_type_checker_delete(type_checker);
gt_timer_delete(t);
gt_array_delete(arr);
gt_str_delete(speclib);
return had_err;
}
int main(int argc, char ** argv)
{
GtNodeStream * in, * score, * out;
GtFile * out_file;
GtError * err;
if (argc != 4)
{
usage(argv[0]);
exit(1);
}
// initilaize genometools
gt_lib_init();
err = gt_error_new();
if (!(in = gt_gff3_in_stream_new_sorted(argv[1])))
{
fprintf(stderr, "Failed to open input stream with arg %s\n", argv[1]);
exit(1);
}
if (!(out_file = gt_file_new(argv[2], "w+", err)))
{
gt_node_stream_delete(in);
fprintf(stderr, "Failed to create output file %s\n", argv[2]);
exit(1);
}
if (!(score = CpGI_score_stream_new(in, argv[3])))
{
gt_file_delete(out_file);
gt_node_stream_delete(in);
fprintf(stderr, "Failed to create CpGI score stream\n");
exit(1);
}
out = gt_gff3_out_stream_new(in, out_file);
if (!(out = gt_gff3_out_stream_new(score, out_file)))
{
gt_node_stream_delete(score);
gt_file_delete(out_file);
gt_node_stream_delete(in);
fprintf(stderr, "Failed to create output stream\n");
exit(1);
}
if (gt_node_stream_pull(out, err))
{
fprintf(stderr, "Failed to pull through out stream\n");
}
// close genome tools
gt_node_stream_delete(out);
gt_node_stream_delete(score);
gt_file_delete(out_file);
gt_node_stream_delete(in);
gt_error_delete(err);
gt_lib_clean();
return 0;
}
static int gt_gff3_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GtError *err)
{
GFF3Arguments *arguments = tool_arguments;
GtTypeChecker *type_checker = NULL;
GtNodeStream *gff3_in_stream,
*sort_stream = NULL,
*load_stream = NULL,
*merge_feature_stream = NULL,
*add_introns_stream = NULL,
*set_source_stream = NULL,
*gff3_out_stream = NULL,
*last_stream;
int had_err = 0;
gt_error_check(err);
gt_assert(arguments);
/* create a gff3 input stream */
gff3_in_stream = gt_gff3_in_stream_new_unsorted(argc - parsed_args,
argv + parsed_args);
if (arguments->verbose && arguments->outfp)
gt_gff3_in_stream_show_progress_bar((GtGFF3InStream*) gff3_in_stream);
if (arguments->checkids)
gt_gff3_in_stream_check_id_attributes((GtGFF3InStream*) gff3_in_stream);
if (!arguments->addids)
gt_gff3_in_stream_disable_add_ids(gff3_in_stream);
last_stream = gff3_in_stream;
/* set different type checker if necessary */
if (gt_typecheck_info_option_used(arguments->tci)) {
type_checker = gt_typecheck_info_create_type_checker(arguments->tci, err);
if (!type_checker)
had_err = -1;
if (!had_err)
gt_gff3_in_stream_set_type_checker(gff3_in_stream, type_checker);
}
/* set offset (if necessary) */
if (!had_err && arguments->offset != GT_UNDEF_WORD)
gt_gff3_in_stream_set_offset(gff3_in_stream, arguments->offset);
/* set offsetfile (if necessary) */
if (!had_err && gt_str_length(arguments->offsetfile)) {
had_err = gt_gff3_in_stream_set_offsetfile(gff3_in_stream,
arguments->offsetfile, err);
}
/* enable strict mode (if necessary) */
if (!had_err && arguments->strict)
gt_gff3_in_stream_enable_strict_mode((GtGFF3InStream*) gff3_in_stream);
/* enable tidy mode (if necessary) */
if (!had_err && arguments->tidy)
gt_gff3_in_stream_enable_tidy_mode((GtGFF3InStream*) gff3_in_stream);
if (!had_err && arguments->fixboundaries)
gt_gff3_in_stream_fix_region_boundaries((GtGFF3InStream*) gff3_in_stream);
/* create load stream (if necessary) */
if (!had_err && arguments->load) {
load_stream = gt_load_stream_new(last_stream);
last_stream = load_stream;
}
/* create sort stream (if necessary) */
if (!had_err && arguments->sort) {
sort_stream = gt_sort_stream_new(last_stream);
last_stream = sort_stream;
}
/* create merge feature stream (if necessary) */
if (!had_err && arguments->mergefeat) {
gt_assert(sort_stream);
merge_feature_stream = gt_merge_feature_stream_new(sort_stream);
last_stream = merge_feature_stream;
}
/* create addintrons stream (if necessary) */
if (!had_err && arguments->addintrons) {
gt_assert(last_stream);
add_introns_stream = gt_add_introns_stream_new(last_stream);
last_stream = add_introns_stream;
}
/* create setsource stream (if necessary) */
if (!had_err && gt_str_length(arguments->newsource) > 0) {
gt_assert(last_stream);
GtNodeVisitor *ssv = gt_set_source_visitor_new(arguments->newsource);
set_source_stream = gt_visitor_stream_new(last_stream, ssv);
last_stream = set_source_stream;
}
/* create gff3 output stream */
if (!had_err && arguments->show) {
gff3_out_stream = gt_gff3_out_stream_new(last_stream, arguments->outfp);
last_stream = gff3_out_stream;
gt_gff3_out_stream_set_fasta_width((GtGFF3OutStream*) last_stream,
arguments->width);
if (arguments->retainids)
gt_gff3_out_stream_retain_id_attributes((GtGFF3OutStream*) last_stream);
}
/* pull the features through the stream and free them afterwards */
if (!had_err)
had_err = gt_node_stream_pull(last_stream, err);
/* free */
gt_node_stream_delete(gff3_out_stream);
gt_node_stream_delete(sort_stream);
gt_node_stream_delete(load_stream);
gt_node_stream_delete(merge_feature_stream);
gt_node_stream_delete(add_introns_stream);
gt_node_stream_delete(set_source_stream);
gt_node_stream_delete(gff3_in_stream);
gt_type_checker_delete(type_checker);
return had_err;
}
static int gt_ltrdigest_runner(GT_UNUSED int argc, const char **argv,
int parsed_args, void *tool_arguments,
GtError *err)
{
GtLTRdigestOptions *arguments = tool_arguments;
GtNodeStream *gff3_in_stream = NULL,
*gff3_out_stream = NULL,
*pdom_stream = NULL,
*ppt_stream = NULL,
*pbs_stream = NULL,
*tab_out_stream = NULL,
*sa_stream = NULL,
*last_stream = NULL;
int had_err = 0,
tests_to_run = 0,
arg = parsed_args;
GtRegionMapping *rmap = NULL;
GtPdomModelSet *ms = NULL;
gt_error_check(err);
gt_assert(arguments);
/* determine and open sequence source */
if (gt_seqid2file_option_used(arguments->s2fi)) {
/* create region mapping */
rmap = gt_seqid2file_region_mapping_new(arguments->s2fi, err);
if (!rmap)
had_err = -1;
} else {
GtEncseqLoader *el;
GtEncseq *encseq;
/* no new-style sequence source option given, fall back to legacy syntax */
if (argc < 3) {
gt_error_set(err, "missing mandatory argument(s)");
had_err = -1;
}
if (!had_err) {
el = gt_encseq_loader_new();
gt_encseq_loader_disable_autosupport(el);
gt_encseq_loader_require_md5_support(el);
gt_encseq_loader_require_description_support(el);
encseq = gt_encseq_loader_load(el, argv[argc-1], err);
/* XXX: clip off terminal argument */
gt_free((char*) argv[argc-1]);
argv[argc-1] = NULL;
argc--;
gt_encseq_loader_delete(el);
if (!encseq)
had_err = -1;
else {
rmap = gt_region_mapping_new_encseq_seqno(encseq);
gt_encseq_delete(encseq);
}
}
}
gt_assert(had_err || rmap);
/* Always search for PPT. */
tests_to_run |= GT_LTRDIGEST_RUN_PPT;
/* Open tRNA library if given. */
if (!had_err && arguments->trna_lib
&& gt_str_length(arguments->trna_lib) > 0)
{
tests_to_run |= GT_LTRDIGEST_RUN_PBS;
arguments->trna_lib_bs = gt_bioseq_new(gt_str_get(arguments->trna_lib),
err);
if (gt_error_is_set(err))
had_err = -1;
}
/* Set HMMER cutoffs. */
if (!had_err && gt_str_array_size(arguments->hmm_files) > 0)
{
tests_to_run |= GT_LTRDIGEST_RUN_PDOM;
if (!strcmp(gt_str_get(arguments->cutoffs), "GA")) {
arguments->cutoff = GT_PHMM_CUTOFF_GA;
} else if (!strcmp(gt_str_get(arguments->cutoffs), "TC")) {
arguments->cutoff = GT_PHMM_CUTOFF_TC;
} else if (!strcmp(gt_str_get(arguments->cutoffs), "NONE")) {
arguments->cutoff = GT_PHMM_CUTOFF_NONE;
} else {
gt_error_set(err, "invalid cutoff setting!");
had_err = -1;
}
}
if (!had_err) {
last_stream = gff3_in_stream = gt_gff3_in_stream_new_sorted(argv[arg]);
}
if (!had_err && gt_str_array_size(arguments->hmm_files) > 0) {
GtNodeVisitor *pdom_v;
ms = gt_pdom_model_set_new(arguments->hmm_files, err);
if (ms != NULL) {
pdom_v = gt_ltrdigest_pdom_visitor_new(ms, arguments->evalue_cutoff,
arguments->chain_max_gap_length,
arguments->cutoff, rmap, err);
if (pdom_v == NULL)
had_err = -1;
if (!had_err) {
gt_ltrdigest_pdom_visitor_set_source_tag((GtLTRdigestPdomVisitor*)
pdom_v,
GT_LTRDIGEST_TAG);
if (arguments->output_all_chains)
gt_ltrdigest_pdom_visitor_output_all_chains((GtLTRdigestPdomVisitor*)
pdom_v);
last_stream = pdom_stream = gt_visitor_stream_new(last_stream, pdom_v);
}
} else had_err = -1;
}
if (!had_err && arguments->trna_lib_bs) {
GtNodeVisitor *pbs_v;
pbs_v = gt_ltrdigest_pbs_visitor_new(rmap, arguments->pbs_radius,
arguments->max_edist,
arguments->alilen,
arguments->offsetlen,
arguments->trnaoffsetlen,
arguments->ali_score_match,
arguments->ali_score_mismatch,
arguments->ali_score_insertion,
arguments->ali_score_deletion,
arguments->trna_lib_bs, err);
if (pbs_v != NULL)
last_stream = pbs_stream = gt_visitor_stream_new(last_stream, pbs_v);
else
had_err = -1;
}
if (!had_err) {
GtNodeVisitor *ppt_v;
ppt_v = gt_ltrdigest_ppt_visitor_new(rmap, arguments->ppt_len,
arguments->ubox_len,
arguments->ppt_pyrimidine_prob,
arguments->ppt_purine_prob,
arguments->bkg_a_prob,
arguments->bkg_g_prob,
arguments->bkg_t_prob,
arguments->bkg_c_prob,
arguments->ubox_u_prob,
arguments->ppt_radius,
arguments->max_ubox_dist, err);
if (ppt_v != NULL)
last_stream = ppt_stream = gt_visitor_stream_new(last_stream, ppt_v);
else
had_err = -1;
}
if (!had_err) {
GtNodeVisitor *sa_v;
sa_v = gt_ltrdigest_strand_assign_visitor_new();
gt_assert(sa_v);
last_stream = sa_stream = gt_visitor_stream_new(last_stream, sa_v);
}
if (!had_err)
{
/* attach tabular output stream, if requested */
if (gt_str_length(arguments->prefix) > 0)
{
last_stream = tab_out_stream = gt_ltrdigest_file_out_stream_new(
last_stream,
tests_to_run,
rmap,
gt_str_get(arguments->prefix),
arguments->seqnamelen,
err);
if (!tab_out_stream)
had_err = -1;
if (!had_err && arguments->print_metadata)
{
had_err = gt_ltrdigest_file_out_stream_write_metadata(
(GtLTRdigestFileOutStream*)
tab_out_stream,
tests_to_run,
gt_str_get(arguments->trna_lib),
argv[arg],
arguments->ppt_len,
arguments->ubox_len,
arguments->ppt_radius,
arguments->alilen,
arguments->max_edist,
arguments->offsetlen,
arguments->trnaoffsetlen,
arguments->pbs_radius,
arguments->hmm_files,
arguments->chain_max_gap_length,
arguments->evalue_cutoff,
err);
}
if (!had_err)
{
if (arguments->write_alignments)
gt_ltrdigest_file_out_stream_enable_pdom_alignment_output(
tab_out_stream);
if (arguments->write_aaseqs)
gt_ltrdigest_file_out_stream_enable_aa_sequence_output(
tab_out_stream);
}
}
last_stream = gff3_out_stream = gt_gff3_out_stream_new(last_stream,
arguments->outfp);
/* pull the features through the stream and free them afterwards */
had_err = gt_node_stream_pull(last_stream, err);
}
gt_pdom_model_set_delete(ms);
gt_node_stream_delete(gff3_out_stream);
gt_node_stream_delete(ppt_stream);
gt_node_stream_delete(pbs_stream);
gt_node_stream_delete(sa_stream);
gt_node_stream_delete(pdom_stream);
gt_node_stream_delete(tab_out_stream);
gt_node_stream_delete(gff3_in_stream);
gt_bioseq_delete(arguments->trna_lib_bs);
gt_region_mapping_delete(rmap);
return had_err;
}
static int gt_tir_runner(GT_UNUSED int argc, GT_UNUSED const char **argv,
GT_UNUSED int parsed_args, void *tool_arguments,
GtError *err)
{
GtTirArguments *arguments = tool_arguments;
GtNodeStream *tir_stream = NULL,
*pdom_stream = NULL,
*gff3_out_stream = NULL,
*last_stream = NULL;
GtPdomModelSet *ms = NULL;
GtRegionMapping *rmap = NULL;
int had_err = 0;
gt_error_check(err);
gt_assert(arguments);
tir_stream = gt_tir_stream_new(arguments->str_indexname,
arguments->min_seed_length,
arguments->min_TIR_length,
arguments->max_TIR_length,
arguments->min_TIR_distance,
arguments->max_TIR_distance,
arguments->arbit_scores,
arguments->xdrop_belowscore,
arguments->similarity_threshold,
arguments->best_overlaps,
arguments->no_overlaps,
arguments->min_TSD_length,
arguments->max_TSD_length,
arguments->vicinity,
err);
if (tir_stream == NULL)
return -1;
last_stream = tir_stream;
rmap = gt_region_mapping_new_encseq((GtEncseq*)
gt_tir_stream_get_encseq((GtTIRStream*) tir_stream),
true, false);
gt_assert(rmap);
if (!had_err && gt_str_array_size(arguments->hmm_files) > 0)
{
if (!strcmp(gt_str_get(arguments->cutoffs), "GA")) {
arguments->cutoff = GT_PHMM_CUTOFF_GA;
} else if (!strcmp(gt_str_get(arguments->cutoffs), "TC")) {
arguments->cutoff = GT_PHMM_CUTOFF_TC;
} else if (!strcmp(gt_str_get(arguments->cutoffs), "NONE")) {
arguments->cutoff = GT_PHMM_CUTOFF_NONE;
} else {
gt_error_set(err, "invalid cutoff setting!");
had_err = -1;
}
}
if (!had_err && gt_str_array_size(arguments->hmm_files) > 0) {
GtNodeVisitor *pdom_v;
ms = gt_pdom_model_set_new(arguments->hmm_files, err);
if (ms != NULL) {
pdom_v = gt_ltrdigest_pdom_visitor_new(ms, arguments->cutoff,
arguments->chain_max_gap_length,
arguments->evalue_cutoff, rmap,
err);
if (pdom_v == NULL)
had_err = -1;
if (!had_err) {
last_stream = pdom_stream = gt_visitor_stream_new(last_stream, pdom_v);
gt_ltrdigest_pdom_visitor_set_root_type((GtLTRdigestPdomVisitor*)
pdom_v,
gt_ft_terminal_inverted_repeat_element);
gt_ltrdigest_pdom_visitor_set_source_tag((GtLTRdigestPdomVisitor*)
pdom_v,
"TIRvish");
}
} else had_err = -1;
}
gff3_out_stream = gt_gff3_out_stream_new(last_stream, NULL);
last_stream = gff3_out_stream;
/* pull the features through the stream and free them afterwards */
if (!had_err)
had_err = gt_node_stream_pull(last_stream, err);
gt_node_stream_delete(tir_stream);
gt_node_stream_delete(pdom_stream);
gt_node_stream_delete(gff3_out_stream);
gt_region_mapping_delete(rmap);
gt_pdom_model_set_delete(ms);
return had_err;
}
static int gt_sketch_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GT_UNUSED GtError *err)
{
GtSketchArguments *arguments = tool_arguments;
GtNodeStream *in_stream = NULL,
*add_introns_stream = NULL,
*gff3_out_stream = NULL,
*feature_stream = NULL,
*sort_stream = NULL,
*last_stream;
GtFeatureIndex *features = NULL;
const char *file;
char *seqid = NULL;
GtRange qry_range, sequence_region_range;
GtArray *results = NULL;
GtStyle *sty = NULL;
GtStr *prog, *defaultstylefile = NULL;
GtDiagram *d = NULL;
GtLayout *l = NULL;
GtImageInfo* ii = NULL;
GtCanvas *canvas = NULL;
GtUword height;
bool has_seqid;
int had_err = 0;
gt_error_check(err);
gt_assert(arguments);
prog = gt_str_new();
gt_str_append_cstr_nt(prog, argv[0],
gt_cstr_length_up_to_char(argv[0], ' '));
defaultstylefile = gt_get_gtdata_path(gt_str_get(prog), err);
gt_str_delete(prog);
if (!defaultstylefile)
had_err = -1;
if (!had_err) {
gt_str_append_cstr(defaultstylefile, "/sketch/default.style");
}
file = argv[parsed_args];
if (!had_err) {
/* create feature index */
features = gt_feature_index_memory_new();
parsed_args++;
/* create an input stream */
if (strcmp(gt_str_get(arguments->input), "gff") == 0)
{
in_stream = gt_gff3_in_stream_new_unsorted(argc - parsed_args,
argv + parsed_args);
if (arguments->verbose)
gt_gff3_in_stream_show_progress_bar((GtGFF3InStream*) in_stream);
} else if (strcmp(gt_str_get(arguments->input), "bed") == 0)
{
if (argc - parsed_args == 0)
in_stream = gt_bed_in_stream_new(NULL);
else
in_stream = gt_bed_in_stream_new(argv[parsed_args]);
} else if (strcmp(gt_str_get(arguments->input), "gtf") == 0)
{
if (argc - parsed_args == 0)
in_stream = gt_gtf_in_stream_new(NULL);
else
in_stream = gt_gtf_in_stream_new(argv[parsed_args]);
}
last_stream = in_stream;
/* create add introns stream if -addintrons was used */
if (arguments->addintrons) {
sort_stream = gt_sort_stream_new(last_stream);
add_introns_stream = gt_add_introns_stream_new(sort_stream);
last_stream = add_introns_stream;
}
/* create gff3 output stream if -pipe was used */
if (arguments->pipe) {
gff3_out_stream = gt_gff3_out_stream_new(last_stream, NULL);
last_stream = gff3_out_stream;
}
/* create feature stream */
feature_stream = gt_feature_stream_new(last_stream, features);
/* pull the features through the stream and free them afterwards */
had_err = gt_node_stream_pull(feature_stream, err);
gt_node_stream_delete(feature_stream);
gt_node_stream_delete(gff3_out_stream);
gt_node_stream_delete(sort_stream);
gt_node_stream_delete(add_introns_stream);
gt_node_stream_delete(in_stream);
}
if (!had_err) {
had_err = gt_feature_index_has_seqid(features,
&has_seqid,
gt_str_get(arguments->seqid),
err);
}
/* if seqid is empty, take first one added to index */
if (!had_err && strcmp(gt_str_get(arguments->seqid),"") == 0) {
seqid = gt_feature_index_get_first_seqid(features, err);
if (seqid == NULL) {
gt_error_set(err, "GFF input file must contain a sequence region!");
had_err = -1;
}
}
else if (!had_err && !has_seqid) {
gt_error_set(err, "sequence region '%s' does not exist in GFF input file",
gt_str_get(arguments->seqid));
had_err = -1;
}
else if (!had_err)
seqid = gt_str_get(arguments->seqid);
results = gt_array_new(sizeof (GtGenomeNode*));
if (!had_err) {
had_err = gt_feature_index_get_range_for_seqid(features,
&sequence_region_range,
seqid,
err);
}
if (!had_err) {
qry_range.start = (arguments->start == GT_UNDEF_UWORD ?
sequence_region_range.start :
arguments->start);
qry_range.end = (arguments->end == GT_UNDEF_UWORD ?
sequence_region_range.end :
arguments->end);
}
if (!had_err) {
if (arguments->verbose)
fprintf(stderr, "# of results: "GT_WU"\n", gt_array_size(results));
/* find and load style file */
if (!(sty = gt_style_new(err)))
had_err = -1;
if (gt_str_length(arguments->stylefile) == 0) {
gt_str_append_str(arguments->stylefile, defaultstylefile);
} else {
if (!had_err && gt_file_exists(gt_str_get(arguments->stylefile))) {
if (arguments->unsafe)
gt_style_unsafe_mode(sty);
}
else
{
had_err = -1;
gt_error_set(err, "style file '%s' does not exist!",
gt_str_get(arguments->stylefile));
}
}
if (!had_err)
had_err = gt_style_load_file(sty, gt_str_get(arguments->stylefile), err);
}
if (!had_err) {
/* create and write image file */
if (!(d = gt_diagram_new(features, seqid, &qry_range, sty, err)))
had_err = -1;
if (!had_err && arguments->flattenfiles)
gt_diagram_set_track_selector_func(d, flattened_file_track_selector,
NULL);
if (had_err || !(l = gt_layout_new(d, arguments->width, sty, err)))
had_err = -1;
if (!had_err)
had_err = gt_layout_get_height(l, &height, err);
if (!had_err) {
ii = gt_image_info_new();
if (strcmp(gt_str_get(arguments->format),"pdf")==0) {
canvas = gt_canvas_cairo_file_new(sty, GT_GRAPHICS_PDF,
arguments->width,
height, ii, err);
}
else if (strcmp(gt_str_get(arguments->format),"ps")==0) {
canvas = gt_canvas_cairo_file_new(sty, GT_GRAPHICS_PS,
arguments->width,
height, ii, err);
}
else if (strcmp(gt_str_get(arguments->format),"svg")==0) {
canvas = gt_canvas_cairo_file_new(sty, GT_GRAPHICS_SVG,
arguments->width,
height, ii, err);
}
else {
canvas = gt_canvas_cairo_file_new(sty, GT_GRAPHICS_PNG,
arguments->width,
height, ii, err);
}
if (!canvas)
had_err = -1;
if (!had_err) {
had_err = gt_layout_sketch(l, canvas, err);
}
if (!had_err) {
if (arguments->showrecmaps) {
GtUword i;
const GtRecMap *rm;
for (i = 0; i < gt_image_info_num_of_rec_maps(ii) ;i++) {
char buf[BUFSIZ];
rm = gt_image_info_get_rec_map(ii, i);
(void) gt_rec_map_format_html_imagemap_coords(rm, buf, BUFSIZ);
printf("%s, %s\n",
buf,
gt_feature_node_get_type(gt_rec_map_get_genome_feature(rm)));
}
}
if (arguments->use_streams) {
GtFile *outfile;
GtStr *str = gt_str_new();
gt_canvas_cairo_file_to_stream((GtCanvasCairoFile*) canvas, str);
outfile = gt_file_open(GT_FILE_MODE_UNCOMPRESSED, file, "w+", err);
if (outfile) {
gt_file_xwrite(outfile, gt_str_get_mem(str), gt_str_length(str));
gt_file_delete(outfile);
} else {
had_err = -1;
}
gt_str_delete(str);
} else {
had_err = gt_canvas_cairo_file_to_file((GtCanvasCairoFile*) canvas,
file,
err);
}
}
}
}
/* free */
gt_free(seqid);
gt_canvas_delete(canvas);
gt_layout_delete(l);
gt_image_info_delete(ii);
gt_style_delete(sty);
gt_diagram_delete(d);
gt_array_delete(results);
gt_str_delete(defaultstylefile);
gt_feature_index_delete(features);
return had_err;
}
// Main method
int main(int argc, char * const *argv)
{
GtError *error;
GtLogger *logger;
GtQueue *streams;
GtNodeStream *stream, *last_stream;
CanonGFF3Options options = { NULL, NULL, false };
gt_lib_init();
error = gt_error_new();
canon_gff3_parse_options(argc, argv + 0, &options, error);
streams = gt_queue_new();
logger = gt_logger_new(true, "", stderr);
stream = gt_gff3_in_stream_new_unsorted(argc - optind, (const char **)
argv+optind);
gt_gff3_in_stream_check_id_attributes((GtGFF3InStream *)stream);
gt_gff3_in_stream_enable_tidy_mode((GtGFF3InStream *)stream);
gt_queue_add(streams, stream);
last_stream = stream;
if(options.infer)
{
GtHashmap *type_parents = gt_hashmap_new(GT_HASH_STRING, gt_free_func,
gt_free_func);
gt_hashmap_add(type_parents, gt_cstr_dup("mRNA"), gt_cstr_dup("gene"));
gt_hashmap_add(type_parents, gt_cstr_dup("tRNA"), gt_cstr_dup("gene"));
stream = agn_infer_parent_stream_new(last_stream,
type_parents);
gt_hashmap_delete(type_parents);
gt_queue_add(streams, stream);
last_stream = stream;
}
stream = agn_gene_stream_new(last_stream, logger);
gt_queue_add(streams, stream);
last_stream = stream;
if(options.source != NULL)
{
GtNodeVisitor *ssv = gt_set_source_visitor_new(options.source);
stream = gt_visitor_stream_new(last_stream, ssv);
gt_queue_add(streams, stream);
last_stream = stream;
}
stream = gt_gff3_out_stream_new(last_stream, options.outstream);
if(!options.infer)
gt_gff3_out_stream_retain_id_attributes((GtGFF3OutStream *)stream);
gt_queue_add(streams, stream);
last_stream = stream;
if(gt_node_stream_pull(last_stream, error) == -1)
{
fprintf(stderr, "[CanonGFF3] error processing node stream: %s",
gt_error_get(error));
}
while(gt_queue_size(streams) > 0)
{
stream = gt_queue_get(streams);
gt_node_stream_delete(stream);
}
gt_queue_delete(streams);
if(options.source != NULL)
gt_str_delete(options.source);
if(options.outstream != NULL)
gt_file_delete(options.outstream);
gt_error_delete(error);
gt_logger_delete(logger);
gt_lib_clean();
return 0;
}