static void canon_gff3_parse_options(int argc, char * const *argv,
CanonGFF3Options *options, GtError *error)
{
int opt = 0;
int optindex = 0;
const char *optstr = "hio:s:v";
const struct option init_options[] =
{
{ "help", no_argument, NULL, 'h' },
{ "infer", no_argument, NULL, 'i' },
{ "outfile", required_argument, NULL, 'o' },
{ "source", required_argument, NULL, 's' },
{ "version", no_argument, NULL, 'v' },
{ NULL, no_argument, NULL, 0 },
};
for(opt = getopt_long(argc, argv, optstr, init_options, &optindex);
opt != -1;
opt = getopt_long(argc, argv, optstr, init_options, &optindex))
{
if(opt == 'h')
{
print_usage(stdout);
exit(0);
}
else if(opt == 'i')
options->infer = true;
else if(opt == 'o')
{
if(options->outstream != NULL)
gt_file_delete(options->outstream);
options->outstream = gt_file_new(optarg, "w", error);
}
else if(opt == 's')
{
if(options->source != NULL)
gt_str_delete(options->source);
options->source = gt_str_new_cstr(optarg);
}
else if(opt == 'v')
{
agn_print_version("CanonGFF3", stdout);
exit(0);
}
}
}
bool gt_file_exists_with_suffix(const char *path, const char *suffix)
{
struct stat statbuf;
GtStr *tmpfilename;
gt_assert(path && suffix);
tmpfilename = gt_str_new_cstr(path);
gt_str_append_cstr(tmpfilename, suffix);
if (stat(gt_str_get(tmpfilename), &statbuf) == 0) {
gt_str_delete(tmpfilename);
return true;
}
gt_str_delete(tmpfilename);
return false;
}
GtLeftborderOutbuffer *gt_leftborderbuffer_new(const char *name,
GtFirstcodesspacelog *fcsl)
{
GtLeftborderOutbuffer *lbbuf = gt_malloc(sizeof (*lbbuf));
lbbuf->totalwrite = 0;
lbbuf->outfilename = gt_str_new();
lbbuf->fp = gt_xtmpfp(lbbuf->outfilename);
lbbuf->nextfree = 0;
lbbuf->allocated = 1024UL;
lbbuf->name = gt_str_new_cstr(name);
lbbuf->spaceuint32_t = gt_malloc(sizeof (*lbbuf->spaceuint32_t) *
lbbuf->allocated);
GT_FCI_ADDWORKSPACE(fcsl,name,
sizeof (*lbbuf->spaceuint32_t) * lbbuf->allocated);
return lbbuf;
}
static int layout_tracks(void *key, void *value, void *data,
GT_UNUSED GtError *err)
{
unsigned long i, max;
GtTrack *track;
GtLayoutTraverseInfo *lti = (GtLayoutTraverseInfo*) data;
GtArray *list = (GtArray*) value;
GtStr *gt_track_key;
const char *type = key;
GtBlock *block;
bool split;
double tmp;
gt_assert(type && list);
/* to get a deterministic layout, we sort the GtBlocks for each type */
gt_array_sort_stable(list, blocklist_block_compare);
block = *(GtBlock**) gt_array_get(list, 0);
gt_track_key = gt_str_new_cstr((char*) key);
if (!gt_style_get_bool(lti->layout->style, "format", "split_lines", &split,
NULL))
split = true;
if (split)
if (!gt_style_get_bool(lti->layout->style, type, "split_lines", &split,
NULL))
split = true;
if (gt_style_get_num(lti->layout->style, type, "max_num_lines", &tmp, NULL))
max = tmp;
else
max = 50;
track = gt_track_new(gt_track_key, max, split,
gt_line_breaker_captions_new(lti->layout,
lti->layout->width,
lti->layout->style));
lti->layout->nof_tracks++;
for (i = 0; i < gt_array_size(list); i++) {
block = *(GtBlock**) gt_array_get(list, i);
gt_track_insert_block(track, block);
}
gt_hashmap_add(lti->layout->tracks, gt_cstr_dup(gt_str_get(gt_track_key)),
track);
gt_str_delete(gt_track_key);
return 0;
}
int gt_hcr_encoder_encode(GtHcrEncoder *hcr_enc, const char *name,
GtTimer *timer, GtError *err)
{
int had_err = 0;
GtStr *name1;
gt_error_check(err);
if (timer != NULL)
gt_timer_show_progress(timer, "write encoding", stdout);
if (hcr_enc->encdesc_encoder != NULL) {
GtCstrIterator *cstr_iterator = gt_fasta_header_iterator_new(hcr_enc->files,
err);
had_err = gt_encdesc_encoder_encode(hcr_enc->encdesc_encoder,
cstr_iterator, name, err);
gt_cstr_iterator_delete(cstr_iterator);
}
if (!had_err)
had_err = hcr_write_seq_qual_data(name, hcr_enc, timer, err);
if (!had_err && gt_log_enabled()) {
name1 = gt_str_new_cstr(name);
gt_str_append_cstr(name1, HCRFILESUFFIX);
gt_log_log("sequences with qualities encoding overview:");
gt_log_log("**>");
if (hcr_enc->page_sampling)
gt_log_log("applied sampling technique: sampling every "GT_WU"th page",
hcr_enc->sampling_rate);
else if (hcr_enc->regular_sampling)
gt_log_log("applied sampling technique: sampling every "GT_WU"th read",
hcr_enc->sampling_rate);
else
gt_log_log("applied sampling technique: none");
gt_log_log("total number of encoded nucleotide sequences with qualities: "
""GT_WU"", hcr_enc->num_of_reads);
gt_log_log("total number of encoded nucleotides: "GT_LLU"",
hcr_enc->seq_encoder->total_num_of_symbols);
gt_log_log("bits per nucleotide encoding: %f",
(gt_file_estimate_size(gt_str_get(name1)) * 8.0) /
hcr_enc->seq_encoder->total_num_of_symbols);
gt_log_log("<**");
gt_str_delete(name1);
}
return had_err;
}
static int gt_compreads_decompress_benchmark(GtHcrDecoder *hcrd,
unsigned long amount,
GtTimer *timer,
GtError *err) {
char qual[BUFSIZ] = {0},
seq[BUFSIZ] = {0};
int had_err = 0;
unsigned long rand,
max_rand = gt_hcr_decoder_num_of_reads(hcrd) - 1,
count;
GtStr *timer_comment = gt_str_new_cstr("extracting ");
GtStr *desc = gt_str_new();
gt_str_append_ulong(timer_comment, amount);
gt_str_append_cstr(timer_comment, " reads of ");
gt_str_append_ulong(timer_comment, max_rand + 1);
gt_str_append_cstr(timer_comment, "!");
if (timer == NULL) {
timer = gt_timer_new_with_progress_description("extract random reads");
gt_timer_start(timer);
}
else {
gt_timer_show_progress(timer, "extract random reads", stdout);
}
gt_log_log("%s",gt_str_get(timer_comment));
for (count = 0; count < amount; count++) {
if (!had_err) {
rand = gt_rand_max(max_rand);
gt_log_log("get read: %lu", rand);
had_err = gt_hcr_decoder_decode(hcrd, rand, seq, qual, desc, err);
gt_log_log("%s",gt_str_get(desc));
gt_log_log("%s",seq);
gt_log_log("%s",qual);
}
}
gt_str_delete(timer_comment);
gt_str_delete(desc);
if (!gt_showtime_enabled())
gt_timer_delete(timer);
return had_err;
}
static int process_fastakeyfile(GtStr *fastakeyfile, int argc,
const char **argv, unsigned long width,
GtFile *outfp, GtError *err)
{
int had_err = 0;
gt_error_check(err);
gt_assert(gt_str_length(fastakeyfile));
if (argc == 0) {
gt_error_set(err,"option -keys requires at least one file argument");
had_err = -1;
}
if (!had_err)
{
GtStr *indexname = gt_str_new_cstr(argv[0]);
if (argc == 1 && gt_deskeysfileexists(indexname))
{
if (gt_extractkeysfromfastaindex(indexname,fastakeyfile,width,err) != 0)
{
had_err = -1;
}
} else
{
GtStrArray *referencefiletab;
int i;
referencefiletab = gt_str_array_new();
for (i = 0; i < argc; i++)
{
gt_str_array_add_cstr(referencefiletab, argv[i]);
}
if (gt_extractkeysfromfastafile(true, outfp, width, fastakeyfile,
referencefiletab, err) != 1)
{
had_err = -1;
}
gt_str_array_delete(referencefiletab);
}
gt_str_delete(indexname);
}
return had_err;
}
static GtStr* create_unique_id(GtGFF3Visitor *gff3_visitor, GtFeatureNode *fn)
{
const char *type;
GtStr *id;
gt_assert(gff3_visitor && fn);
type = gt_feature_node_get_type(fn);
/* increase id counter */
gt_string_distri_add(gff3_visitor->id_counter, type);
/* build id string */
id = gt_str_new_cstr(type);
gt_str_append_ulong(id, gt_string_distri_get(gff3_visitor->id_counter, type));
/* store (unique) id */
gt_hashmap_add(gff3_visitor->feature_node_to_unique_id_str, fn, id);
return id;
}
GtSfxmappedrange *gt_Sfxmappedrange_new(const char *tablename,
GtUword numofentries,
GtSfxmappedrangetype type,
GtSfxmappedrangetransformfunc
transformfunc,
const void *transformfunc_data)
{
GtSfxmappedrange *sfxmappedrange;
sfxmappedrange = gt_malloc(sizeof (*sfxmappedrange));
sfxmappedrange->ptr = NULL;
sfxmappedrange->pagesize = gt_pagesize();
sfxmappedrange->usedptrptr = NULL;
sfxmappedrange->filename = NULL;
sfxmappedrange->writable = false;
sfxmappedrange->entire = NULL;
sfxmappedrange->transformfunc = transformfunc;
sfxmappedrange->transformfunc_data = transformfunc_data;
sfxmappedrange->type = type;
sfxmappedrange->tablename = gt_str_new_cstr(tablename);
sfxmappedrange->currentminindex = sfxmappedrange->currentmaxindex = 0;
sfxmappedrange->indexrange_defined = false;
switch (type)
{
case GtSfxGtBitsequence:
sfxmappedrange->sizeofunit = sizeof (GtBitsequence);
sfxmappedrange->numofunits = GT_NUMOFINTSFORBITS(numofentries);
break;
case GtSfxuint32_t:
sfxmappedrange->sizeofunit = sizeof (uint32_t);
sfxmappedrange->numofunits = (size_t) numofentries;
break;
case GtSfxunsignedlong:
sfxmappedrange->sizeofunit = sizeof (GtUword);
sfxmappedrange->numofunits = (size_t) numofentries;
break;
default:
gt_assert(false);
break;
}
return sfxmappedrange;
}
static GtStr* make_id_unique(GtGFF3Visitor *gff3_visitor, GtFeatureNode *fn)
{
GtUword i = 1;
GtStr *id = gt_str_new_cstr(gt_feature_node_get_attribute(fn, "ID"));
if (gt_cstr_table_get(gff3_visitor->used_ids, gt_str_get(id))) {
GtStr *buf = gt_str_new();
while (!id_string_is_unique(id, buf, gff3_visitor->used_ids, i++));
gt_warning("feature ID \"%s\" not unique: changing to %s", gt_str_get(id),
gt_str_get(buf));
gt_str_set(id, gt_str_get(buf));
gt_str_delete(buf);
}
/* update table with the new id */
gt_cstr_table_add(gff3_visitor->used_ids, gt_str_get(id));
/* store (unique) id */
gt_hashmap_add(gff3_visitor->feature_node_to_unique_id_str, fn, id);
return id;
}
bool gt_tool_iterator_next(GtToolIterator *tool_iterator, const char **name,
GtTool **tool)
{
ToolIterationInfo tii;
gt_assert(tool_iterator && name && tool);
if (gt_array_size(tool_iterator->tool_stack)) {
ToolEntry *entry = gt_array_pop(tool_iterator->tool_stack);
*name = entry->name;
*tool = entry->tool;
if (tool_iterator->prefixptr) {
gt_str_reset(tool_iterator->prefixptr);
if (entry->prefix) {
gt_str_append_str(tool_iterator->prefixptr, entry->prefix);
gt_str_append_char(tool_iterator->prefixptr, tool_iterator->prefixsep);
}
}
if (gt_tool_is_toolbox(entry->tool)) {
GtToolbox *toolbox;
GtArray *toollist;
GtStr *myprefix;
myprefix =
gt_str_new_cstr(entry->prefix ? gt_str_get(entry->prefix) : "");
gt_str_append_cstr(myprefix, entry->name);
toolbox = gt_tool_get_toolbox(entry->tool);
toollist = gt_array_new(sizeof (ToolEntry));
tii.arr = toollist;
tii.str = myprefix;
gt_toolbox_iterate(toolbox, add_tool_to_stack, &tii);
if (gt_array_size(toollist)) {
gt_array_reverse(toollist); /* alphabetical order */
gt_array_add_array(tool_iterator->tool_stack, toollist);
}
gt_array_delete(toollist);
gt_str_delete(myprefix);
} else
gt_str_delete(entry->prefix);
return true;
}
else
return false;
}
GtTypeChecker* gt_typecheck_info_create_type_checker(const GtTypecheckInfo *tci,
GtError *err)
{
GtTypeChecker *type_checker = NULL;
int had_err = 0;
gt_error_check(err);
gt_assert(tci);
if (tci->typecheck_built_in)
type_checker = gt_type_checker_builtin_new();
else {
GtStr *obo_file;
gt_assert(gt_option_is_set(tci->typecheck_option));
if (!gt_str_length(tci->typecheck)) {
/* a. */
if (!(obo_file = get_obo_path(err)))
had_err = -1;
if (!had_err)
gt_str_append_cstr(obo_file, "sofa.obo");
}
else if (gt_file_exists(gt_str_get(tci->typecheck))) {
/* b. */
obo_file = gt_str_new_cstr(gt_str_get(tci->typecheck));
}
else {
/* c. */
if (!(obo_file = get_obo_path(err)))
had_err = -1;
if (!had_err) {
gt_str_append_str(obo_file, tci->typecheck);
gt_str_append_cstr(obo_file, ".obo");
}
}
if (!had_err)
type_checker = gt_type_checker_obo_new(gt_str_get(obo_file), err);
gt_str_delete(obo_file);
}
return type_checker;
}
static void orf_attach_results_to_gff3(GtFeatureNode *gf,
GtRange orf_rng, unsigned int orf_frame,
GtStrand strand, GT_UNUSED GtError *err)
{
GtGenomeNode *child;
GtStr *tag;
tag = gt_str_new_cstr(GT_ORF_FINDER_TAG);
orf_rng.start++; orf_rng.end++;
GtFeatureNodeIterator *gfi;
GtFeatureNode *curnode = NULL, *parent_node = NULL;
GtRange gfi_range;
char frame_buf[3];
sprintf(frame_buf, "%d", orf_frame);
gfi = gt_feature_node_iterator_new(gf);
while ((curnode = gt_feature_node_iterator_next(gfi))) {
if (strcmp(gt_feature_node_get_type(curnode),
(const char*) GT_ORF_TYPE) != 0) {
gfi_range = gt_genome_node_get_range((GtGenomeNode*) curnode);
if (gt_range_contains(&gfi_range, &orf_rng)) {
parent_node = curnode;
}
}
}
if (parent_node) {
child = gt_feature_node_new(gt_genome_node_get_seqid((GtGenomeNode*) gf),
GT_ORF_TYPE,
orf_rng.start,
orf_rng.end,
strand);
gt_feature_node_set_source((GtFeatureNode*) child, tag);
gt_feature_node_set_attribute((GtFeatureNode*) child, "frame", frame_buf);
gt_feature_node_add_child(parent_node,(GtFeatureNode*) child);
}
gt_str_delete(tag);
gt_feature_node_iterator_delete(gfi);
}
/* takes ownership of <files> */
static GtNodeStream* gff3_in_stream_plain_new(GtStrArray *files,
bool ensure_sorting)
{
GtNodeStream *ns = gt_node_stream_create(gt_gff3_in_stream_plain_class(),
ensure_sorting);
GtGFF3InStreamPlain *gff3_in_stream_plain = gff3_in_stream_plain_cast(ns);
gff3_in_stream_plain->next_file = 0;
gff3_in_stream_plain->files = files;
gff3_in_stream_plain->stdinstr = gt_str_new_cstr("stdin");
gff3_in_stream_plain->ensure_sorting = ensure_sorting;
gff3_in_stream_plain->stdin_argument = false;
gff3_in_stream_plain->file_is_open = false;
gff3_in_stream_plain->fpin = NULL;
gff3_in_stream_plain->line_number = 0;
gff3_in_stream_plain->genome_node_buffer = gt_queue_new();
gff3_in_stream_plain->checkids = false;
gff3_in_stream_plain->checkregions = false;
gff3_in_stream_plain->gff3_parser = gt_gff3_parser_new(NULL);
gff3_in_stream_plain->used_types = gt_cstr_table_new();
gff3_in_stream_plain->progress_bar = false;
return ns;
}
void feature_in_stream_init(GtFeatureInStream *stream)
{
GtUword i;
GtError *error = gt_error_new();
stream->seqids = gt_feature_index_get_seqids(stream->fi, error);
stream->seqindex = 0;
for (i = 0; i < gt_str_array_size(stream->seqids); i++)
{
const char *seqid = gt_str_array_get(stream->seqids, i);
GtRange seqrange;
if (stream->useorig)
gt_feature_index_get_orig_range_for_seqid(stream->fi, &seqrange, seqid,
error);
else
gt_feature_index_get_range_for_seqid(stream->fi, &seqrange, seqid, error);
GtStr *seqstr = gt_str_new_cstr(seqid);
GtGenomeNode *rn = gt_region_node_new(seqstr, seqrange.start, seqrange.end);
gt_queue_add(stream->regioncache, rn);
gt_str_delete(seqstr);
}
gt_error_delete(error);
}
static int gtf_in_stream_process_file(GtGTFInStream *gtf_in_stream,
GtError *err)
{
GtGTFParser *gtf_parser;
GtStr *filenamestr;
GtFile *fpin;
int had_err = 0;
gt_error_check(err);
gt_assert(gtf_in_stream);
gtf_parser = gt_gtf_parser_new(gtf_in_stream->type_checker);
/* open input file */
if (gtf_in_stream->filename) {
if (!(fpin = gt_file_new(gtf_in_stream->filename, "r", err)))
had_err = -1;
}
else
fpin = NULL;
/* parse input file */
if (!had_err) {
filenamestr = gt_str_new_cstr(gtf_in_stream->filename
? gtf_in_stream->filename : "stdin");
had_err = gt_gtf_parser_parse(gtf_parser, gtf_in_stream->genome_node_buffer,
filenamestr, fpin, gtf_in_stream->tidy, err);
gt_str_delete(filenamestr);
}
/* close input file, if necessary */
gt_file_delete(fpin);
/* free */
gt_gtf_parser_delete(gtf_parser);
return had_err;
}
GtXRFChecker* gt_xrfcheck_info_create_xrf_checker(const GtXRFCheckInfo *xci,
GtError *err)
{
GtXRFChecker *xrf_checker = NULL;
int had_err = 0;
GtStr *xrf_file;
gt_error_check(err);
gt_assert(xci);
gt_assert(gt_option_is_set(xci->xrfcheck_option));
if (!gt_str_length(xci->xrfcheck)) {
/* a. */
if (!(xrf_file = get_xrf_path(err)))
had_err = -1;
if (!had_err)
gt_str_append_cstr(xrf_file, "GO.xrf_abbr");
}
else if (gt_file_exists(gt_str_get(xci->xrfcheck))) {
/* b. */
xrf_file = gt_str_new_cstr(gt_str_get(xci->xrfcheck));
}
else {
/* c. */
if (!(xrf_file = get_xrf_path(err)))
had_err = -1;
if (!had_err) {
gt_str_append_str(xrf_file, xci->xrfcheck);
gt_str_append_cstr(xrf_file, ".xrf_abbr");
}
}
if (!had_err)
xrf_checker = gt_xrf_checker_new(gt_str_get(xrf_file), err);
gt_str_delete(xrf_file);
return xrf_checker;
}
static GtIndexOptions* gt_index_options_new(void)
{
GtIndexOptions *oi = gt_malloc(sizeof *oi);
oi->algbounds = gt_str_array_new();
oi->dir = gt_str_new_cstr("fwd");
oi->indexname = NULL;
oi->kysargumentstring = gt_str_new();
oi->lcpdist = false;
oi->maximumspace = 0UL; /* in bytes */
oi->memlimit = gt_str_new();
oi->numofparts = 1U;
oi->option = NULL;
oi->optionalgbounds = NULL;
oi->optioncmpcharbychar = NULL;
oi->optiondifferencecover = NULL;
oi->optionmaxwidthrealmedian = NULL;
oi->optionmemlimit = NULL;
oi->optionoutbcktab = NULL;
oi->optionoutbwttab = NULL;
oi->optionoutlcptab = NULL;
oi->optionoutsuftab = NULL;
oi->optionparts = NULL;
oi->optionprefixlength = NULL;
oi->optionspmopt = NULL;
oi->optionstorespecialcodes = NULL;
oi->outbcktab = false;
oi->outbwttab = false;
oi->outkyssort = false;
oi->outkystab = false;
oi->outlcptab = false;
oi->outsuftab = false; /* only defined for GT_INDEX_OPTIONS_ESA */
oi->prefixlength = GT_PREFIXLENGTH_AUTOMATIC;
oi->swallow_tail = false;
oi->type = GT_INDEX_OPTIONS_UNDEFINED;
return oi;
}
static int sequence_region_lua_new(lua_State *L)
{
GtGenomeNode **rn;
GtUword startpos, endpos;
const char *seqid;
GtStr *seqid_str;
gt_assert(L);
/* get_check parameters */
seqid = luaL_checkstring(L, 1);
startpos = luaL_checklong(L, 2);
endpos = luaL_checklong(L, 3);
luaL_argcheck(L, startpos > 0, 2, "must be > 0");
luaL_argcheck(L, endpos > 0, 3, "must be > 0");
luaL_argcheck(L, startpos <= endpos, 2, "must be <= endpos");
/* construct object */
rn = lua_newuserdata(L, sizeof (GtGenomeNode*));
seqid_str = gt_str_new_cstr(seqid);
*rn = gt_region_node_new(seqid_str, startpos, endpos);
gt_str_delete(seqid_str);
gt_assert(*rn);
luaL_getmetatable(L, GENOME_NODE_METATABLE);
lua_setmetatable(L, -2);
return 1;
}
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;
}
static int bioseq_fill(GtBioseq *bs, bool recreate, GtError *err)
{
GtStr *bioseq_index_file = NULL,
*bioseq_ois_file = NULL,
*bioseq_sds_file = NULL,
*bioseq_md5_file = NULL,
*bioseq_des_file = NULL;
int had_err = 0;
GtStr *bioseq_basename;
gt_assert(!bs->encseq);
if (bs->use_stdin)
bioseq_basename = gt_str_new_cstr("stdin");
else
bioseq_basename = bs->sequence_file;
/* construct file names */
bioseq_index_file = gt_str_clone(bioseq_basename);
gt_str_append_cstr(bioseq_index_file, GT_ENCSEQFILESUFFIX);
bioseq_ois_file = gt_str_clone(bioseq_basename);
gt_str_append_cstr(bioseq_ois_file, GT_OISTABFILESUFFIX);
bioseq_sds_file = gt_str_clone(bioseq_basename);
gt_str_append_cstr(bioseq_sds_file, GT_SDSTABFILESUFFIX);
bioseq_md5_file = gt_str_clone(bioseq_basename);
gt_str_append_cstr(bioseq_md5_file, GT_MD5TABFILESUFFIX);
bioseq_des_file = gt_str_clone(bioseq_basename);
gt_str_append_cstr(bioseq_des_file, GT_DESTABFILESUFFIX);
/* construct the bioseq files if necessary */
if (recreate || bs->use_stdin ||
!gt_file_exists(gt_str_get(bioseq_index_file)) ||
!gt_file_exists(gt_str_get(bioseq_ois_file)) ||
!gt_file_exists(gt_str_get(bioseq_sds_file)) ||
!gt_file_exists(gt_str_get(bioseq_md5_file)) ||
!gt_file_exists(gt_str_get(bioseq_des_file)) ||
gt_file_is_newer(gt_str_get(bs->sequence_file),
gt_str_get(bioseq_index_file))) {
had_err = construct_bioseq_files(bs, bioseq_basename, err);
}
if (!had_err) {
GtEncseqLoader *el = gt_encseq_loader_new();
gt_encseq_loader_disable_autosupport(el);
gt_encseq_loader_require_lossless_support(el);
gt_encseq_loader_require_description_support(el);
gt_encseq_loader_require_md5_support(el);
gt_encseq_loader_require_multiseq_support(el);
bs->encseq = gt_encseq_loader_load(el, gt_str_get(bioseq_basename), err);
if (bs->encseq == NULL) {
had_err = -1;
gt_assert(gt_error_is_set(err));
}
gt_encseq_loader_delete(el);
}
if (!had_err) {
gt_assert(bs->encseq);
}
/* free */
if (bs->use_stdin)
gt_str_delete(bioseq_basename);
gt_str_delete(bioseq_index_file);
gt_str_delete(bioseq_ois_file);
gt_str_delete(bioseq_md5_file);
gt_str_delete(bioseq_sds_file);
gt_str_delete(bioseq_des_file);
return had_err;
}
static int gt_sketch_page_runner(GT_UNUSED int argc,
const char **argv,
int parsed_args,
void *tool_arguments,
GtError *err)
{
SketchPageArguments *arguments = tool_arguments;
int had_err = 0;
GtFeatureIndex *features = NULL;
GtRange qry_range, sequence_region_range;
GtStyle *sty = NULL;
GtStr *prog, *gt_style_file;
GtDiagram *d = NULL;
GtLayout *l = NULL;
GtBioseq *bioseq = NULL;
GtCanvas *canvas = NULL;
const char *seqid = NULL, *outfile;
unsigned long start, height, num_pages = 0;
double offsetpos, usable_height;
cairo_surface_t *surf = NULL;
cairo_t *cr = NULL;
GtTextWidthCalculator *twc;
gt_error_check(err);
features = gt_feature_index_memory_new();
if (cairo_version() < CAIRO_VERSION_ENCODE(1, 8, 6))
gt_warning("Your cairo library (version %s) is older than version 1.8.6! "
"These versions contain a bug which may result in "
"corrupted PDF output!", cairo_version_string());
/* get style */
sty = gt_style_new(err);
if (gt_str_length(arguments->stylefile) == 0)
{
prog = gt_str_new();
gt_str_append_cstr_nt(prog, argv[0],
gt_cstr_length_up_to_char(argv[0], ' '));
gt_style_file = gt_get_gtdata_path(gt_str_get(prog), err);
gt_str_delete(prog);
gt_str_append_cstr(gt_style_file, "/sketch/default.style");
}
else
{
gt_style_file = gt_str_ref(arguments->stylefile);
}
had_err = gt_style_load_file(sty, gt_str_get(gt_style_file), err);
outfile = argv[parsed_args];
if (!had_err)
{
/* get features */
had_err = gt_feature_index_add_gff3file(features, argv[parsed_args+1], err);
if (!had_err && gt_str_length(arguments->seqid) == 0) {
seqid = gt_feature_index_get_first_seqid(features);
if (seqid == NULL)
{
gt_error_set(err, "GFF input file must contain a sequence region!");
had_err = -1;
}
}
else if (!had_err
&& !gt_feature_index_has_seqid(features,
gt_str_get(arguments->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);
}
/* set text */
if (gt_str_length(arguments->text) == 0)
{
gt_str_delete(arguments->text);
arguments->text = gt_str_new_cstr(argv[parsed_args+1]);
}
if (!had_err)
{
/* set display range */
gt_feature_index_get_range_for_seqid(features, &sequence_region_range,
seqid);
qry_range.start = (arguments->range.start == GT_UNDEF_ULONG ?
sequence_region_range.start :
arguments->range.start);
qry_range.end = (arguments->range.end == GT_UNDEF_ULONG ?
sequence_region_range.end :
arguments->range.end);
/* set output format */
if (strcmp(gt_str_get(arguments->format), "pdf") == 0)
{
surf = cairo_pdf_surface_create(outfile,
mm_to_pt(arguments->pwidth),
mm_to_pt(arguments->pheight));
}
else if (strcmp(gt_str_get(arguments->format), "ps") == 0)
{
surf = cairo_ps_surface_create(outfile,
mm_to_pt(arguments->pwidth),
mm_to_pt(arguments->pheight));
}
gt_log_log("created page with %.2f:%.2f dimensions\n",
mm_to_pt(arguments->pwidth),
mm_to_pt(arguments->pheight));
offsetpos = TEXT_SPACER + arguments->theight + TEXT_SPACER;
usable_height = mm_to_pt(arguments->pheight)
- arguments->theight
- arguments->theight
- 4*TEXT_SPACER;
if (gt_str_length(arguments->seqfile) > 0) {
bioseq = gt_bioseq_new(gt_str_get(arguments->seqfile), err);
}
cr = cairo_create(surf);
cairo_set_font_size(cr, 8);
twc = gt_text_width_calculator_cairo_new(cr, sty);
for (start = qry_range.start; start <= qry_range.end;
start += arguments->width)
{
GtRange single_range;
GtCustomTrack *ct = NULL;
const char *seq;
single_range.start = start;
single_range.end = start + arguments->width;
if (had_err)
break;
d = gt_diagram_new(features, seqid, &single_range, sty, err);
if (!d) {
had_err = -1;
break;
}
if (bioseq) {
seq = gt_bioseq_get_sequence(bioseq, 0);
ct = gt_custom_track_gc_content_new(seq,
gt_bioseq_get_sequence_length(bioseq, 0),
800, 70, 0.4, true);
gt_diagram_add_custom_track(d, ct);
}
l = gt_layout_new_with_twc(d, mm_to_pt(arguments->width), sty, twc, err);
had_err = gt_layout_get_height(l, &height, err);
if (!had_err) {
if (gt_double_smaller_double(usable_height - 10 - 2*TEXT_SPACER
- arguments->theight, offsetpos + height))
{
draw_header(cr, gt_str_get(arguments->text), argv[parsed_args+1],
seqid, num_pages, mm_to_pt(arguments->pwidth),
mm_to_pt(arguments->pheight),
arguments->theight);
cairo_show_page(cr);
offsetpos = TEXT_SPACER + arguments->theight + TEXT_SPACER;
num_pages++;
}
canvas = gt_canvas_cairo_context_new(sty,
cr,
offsetpos,
mm_to_pt(arguments->pwidth),
height,
NULL,
err);
if (!canvas)
had_err = -1;
offsetpos += height;
if (!had_err)
had_err = gt_layout_sketch(l, canvas, err);
}
gt_canvas_delete(canvas);
gt_layout_delete(l);
gt_diagram_delete(d);
if (ct)
gt_custom_track_delete(ct);
}
draw_header(cr, gt_str_get(arguments->text), argv[parsed_args+1], seqid,
num_pages, mm_to_pt(arguments->pwidth),
mm_to_pt(arguments->pheight),
arguments->theight);
cairo_show_page(cr);
num_pages++;
gt_log_log("finished, should be %lu pages\n", num_pages);
gt_text_width_calculator_delete(twc);
cairo_destroy(cr);
cairo_surface_flush(surf);
cairo_surface_finish(surf);
cairo_surface_destroy(surf);
cairo_debug_reset_static_data();
if (bioseq)
gt_bioseq_delete(bioseq);
gt_style_delete(sty);
gt_str_delete(gt_style_file);
gt_feature_index_delete(features);
}
return had_err;
}
static int gt_compreads_compress_arguments_check(GT_UNUSED int rest_argc,
void *tool_arguments,
GtError *err)
{
int had_err = 0;
GtCsrHcrEncodeArguments *arguments = tool_arguments;
GtSplitter *splitter = NULL;
GtStr *buffer;
gt_error_check(err);
gt_assert(arguments);
if (gt_str_array_size(arguments->files) == 0) {
gt_error_set(err, "option \"-files\" is mandatory and requires"
" at least one filename as argument!");
had_err = -1;
}
if (!had_err) {
if (gt_str_length(arguments->name) == 0) {
if (gt_str_array_size(arguments->files) > 1UL) {
gt_error_set(err, "option \"-name\" needs to be specified"
" if more than one file is given");
had_err = -1;
}
else {
GtUword i;
char *basename;
splitter = gt_splitter_new();
basename = gt_basename(gt_str_array_get(arguments->files, 0));
buffer = gt_str_new_cstr(basename);
gt_splitter_split(splitter, gt_str_get(buffer), gt_str_length(buffer),
'.');
for (i = 0; i < gt_splitter_size(splitter) - 1; i++) {
gt_str_append_cstr(arguments->name,
gt_splitter_get_token(splitter, i));
if (i < gt_splitter_size(splitter) - 2)
gt_str_append_char(arguments->name, '.');
}
gt_free(basename);
gt_splitter_delete(splitter);
gt_str_delete(buffer);
}
}
}
if (!had_err) {
char *sampling_type = gt_str_get(arguments->method);
static const char *methods[] = { "page", "regular", "none" };
if (!strcmp(methods[0], sampling_type)) {
arguments->pagewise = true;
if (arguments->srate == GT_UNDEF_UWORD)
arguments->srate = GT_SAMPLING_DEFAULT_PAGE_RATE;
else if (arguments->srate == 0) {
gt_error_set(err, "page sampling was chosen, but sampling"
" rate was set to "GT_WU"! this seems wrong.",
arguments->srate);
had_err = -1;
}
}
else if (!strcmp(methods[1], sampling_type)) {
arguments->regular = true;
if (arguments->srate == GT_UNDEF_UWORD)
arguments->srate = GT_SAMPLING_DEFAULT_REGULAR_RATE;
else if (arguments->srate == 0) {
gt_error_set(err, "regular sampling was chosen, but sampling rate "
" was set to "GT_WU"! this seems wrong.",
arguments->srate);
had_err = -1;
}
}
else if (!strcmp(methods[2], sampling_type)) {
if (arguments->srate == GT_UNDEF_UWORD)
arguments->srate = 0;
else if (arguments->srate != 0) {
gt_error_set(err, "no sampling was chosen, but sampling rate was"
" set to "GT_WU"! this seems wrong.",
arguments->srate);
had_err = -1;
}
}
else {
gt_error_set(err, "somethings wrong with the stype option");
had_err = -1;
}
}
if (!had_err) {
if (arguments->arg_range.start != GT_UNDEF_UWORD) {
if (arguments->arg_range.start <= (GtUword) UINT_MAX) {
gt_safe_assign(arguments->qrng.start, arguments->arg_range.start);
if (arguments->arg_range.end <= (GtUword) UINT_MAX)
gt_safe_assign(arguments->qrng.end, arguments->arg_range.end);
else
had_err = -1;
}
else
had_err = -1;
}
if (had_err)
gt_error_set(err, "Range for qualities: value to large! larger than %u",
UINT_MAX);
}
return had_err;
}
static int snp_annotator_classify_snp(GtSNPAnnotatorVisitor *sav,
GtFeatureNode *mRNA,
GtFeatureNode *snp,
GtUword variant_pos,
GtUword variant_idx,
char variant_char,
#ifndef NDEBUG
GT_UNUSED char reference_char,
#endif
GT_UNUSED GtError *err)
{
int had_err = 0;
char *mrnaseq;
const char *variant_effect = NULL;
gt_assert(mRNA && snp && sav);
gt_log_log("processing variant char %c for SNP %s\n",
variant_char, gt_feature_node_get_attribute(snp, "Dbxref"));
mrnaseq = gt_hashmap_get(sav->rnaseqs, mRNA);
gt_assert(mrnaseq);
if (mrnaseq) {
char codon[3],
variant_codon[3];
GtStr *effect_string;
char oldamino,
newamino;
GT_UNUSED GtUword mrnalen;
GtUword startpos = variant_pos / GT_CODON_LENGTH,
variantoffset = variant_pos % GT_CODON_LENGTH;
mrnalen = strlen(mrnaseq);
gt_assert(variant_pos < mrnalen);
variant_codon[0] = codon[0] = mrnaseq[3*startpos];
variant_codon[1] = codon[1] = mrnaseq[3*startpos+1];
variant_codon[2] = codon[2] = mrnaseq[3*startpos+2];
variant_codon[variantoffset] = variant_char;
#ifndef NDEBUG
gt_assert(toupper(codon[variantoffset]) == toupper(reference_char));
#endif
if (gt_trans_table_is_stop_codon(sav->tt, codon[0], codon[1], codon[2])) {
if (gt_trans_table_is_stop_codon(sav->tt, variant_codon[0],
variant_codon[1], variant_codon[2])) {
variant_effect = gt_symbol(GT_SNP_SYNONYMOUS_STOP_EFFECT);
} else {
variant_effect = gt_symbol(GT_SNP_STOP_LOST_EFFECT);
}
} else {
if (gt_trans_table_is_stop_codon(sav->tt, variant_codon[0],
variant_codon[1], variant_codon[2])) {
variant_effect = gt_symbol(GT_SNP_NONSENSE_EFFECT);
} else {
had_err = gt_trans_table_translate_codon(sav->tt, codon[0], codon[1],
codon[2], &oldamino, err);
if (!had_err) {
had_err = gt_trans_table_translate_codon(sav->tt, variant_codon[0],
variant_codon[1],
variant_codon[2],
&newamino, err);
}
if (!had_err) {
if (newamino == oldamino) {
variant_effect = gt_symbol(GT_SNP_SYNONYMOUS_AMINO_EFFECT);
} else {
variant_effect = gt_symbol(GT_SNP_MISSENSE_EFFECT);
}
}
}
}
if (!had_err) {
const char *var_attrib;
gt_assert(variant_effect != NULL);
if ((var_attrib = gt_feature_node_get_attribute(snp,
GT_GVF_VARIANT_EFFECT))) {
effect_string = gt_str_new_cstr(var_attrib);
gt_str_append_cstr(effect_string, ",");
gt_str_append_cstr(effect_string, variant_effect);
} else {
effect_string = gt_str_new_cstr(variant_effect);
}
gt_str_append_cstr(effect_string, " ");
gt_str_append_ulong(effect_string, variant_idx);
gt_str_append_cstr(effect_string, " ");
gt_str_append_cstr(effect_string, gt_feature_node_get_type(mRNA));
gt_str_append_cstr(effect_string, " ");
gt_str_append_cstr(effect_string,
gt_feature_node_get_attribute(mRNA, GT_GFF_ID));
gt_feature_node_set_attribute(snp, GT_GVF_VARIANT_EFFECT,
gt_str_get(effect_string));
gt_str_reset(effect_string);
gt_str_delete(effect_string);
}
}
return had_err;
}
int mg_curl(ParseStruct *parsestruct_ptr,
GtUword hit_counter, GtError * err)
{
int had_err = 0,
curl_errornr = 0;
/* Laenge der aus dem XML-File stammenden Hit-DNA-Sequenz */
GtUword seq_len;
GtWord numb_from = 0, numb_to = 0, numb_diff = 0;
GtStr *seq_var,
*http_adr;
MemoryStruct memorystruct;
/* char-Zeiger auf die HTTP-Adresse des cgi-Skriptes efetch von NCBI */
char *http_adr_ptr,
*seq_pos; /* char-Zeiger, wird benutzt zum
Auslesen der Sequenzinformation
aus dem XML-File, welche
Ergebnis der efetch-Anfrage ist */
const char *curlerror;
/* Curl-Handle */
CURL *curl_handle;
/* char-Zeiger auf die Daten ist NULL */
memorystruct.memory = NULL;
/* noch keine Daten eingetragen bzw. abgespeichert */
memorystruct.size = 0;
/* Zwischenspeicher fuer die Sequnezinformation, da die GtStrArray-Klasse
keine Funktion zum begrenzten Einfuegen eines Strings zur Verfuegung
stellt; setzen des ersten Teils der HTTP-Adresse */
seq_var = gt_str_new();
http_adr =
gt_str_new_cstr
("http://www.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=");
/* Check der Umgebungsvariablen */
gt_error_check(err);
curl_global_init(CURL_GLOBAL_ALL);
/* initialisieren der curl-session */
curl_handle = curl_easy_init();
/* Zusammensetzen der http-Adresse durch Anhaengen der query-GI-Nummer,
des Hit-from, des Hit-to Wertes und des Rueckgabetyps an den ersten
Teil der HTTP-Adresse */
gt_str_append_str(http_adr, ARGUMENTSSTRUCT(curl_fcgi_db));
gt_str_append_cstr(http_adr, "&id=gi|");
gt_str_append_str(http_adr, parsestruct_ptr->hit_gi_nr_tmp);
gt_str_append_cstr(http_adr, "&seq_start=");
gt_str_append_cstr(http_adr,
gt_str_array_get(MATRIXSTRUCT(hit_from), hit_counter));
gt_str_append_cstr(http_adr, "&seq_stop=");
gt_str_append_cstr(http_adr,
gt_str_array_get(MATRIXSTRUCT(hit_to), hit_counter));
gt_str_append_cstr(http_adr, "&retmode=xml");
/* char-Zeiger wird benoetigt, da curl_easy_setopt als 3. Parameter
einen char-Zeiger erwartet */
http_adr_ptr = gt_str_get(http_adr);
/* festlegen, welche HTTP-Adresse aufgerufen werden soll */
curl_easy_setopt(curl_handle, CURLOPT_URL, http_adr_ptr);
/* die empfangenen Daten werden an die Funktion WriteMemoryCallback
gesendet, wo Speicherplatz reserviert und die Daten in diesen
Speicherbereich kopiert werden */
curl_easy_setopt(curl_handle, CURLOPT_WRITEFUNCTION,
WriteMemoryCallback);
/* Die Daten werden in die Struktur eingetragen */
curl_easy_setopt(curl_handle, CURLOPT_WRITEDATA, (void *) &memorystruct);
/* setzen des user-agent field, da einige Server diesen voraussetzen */
curl_easy_setopt(curl_handle, CURLOPT_USERAGENT, "libcurl-agent/1.0");
/* Anfrage wird ausgefuehrt */
curl_errornr = curl_easy_perform(curl_handle);
curlerror = curl_easy_strerror(curl_errornr);
if (curl_errornr)
{
gt_error_set(err,
"an error occurred during curl-processing (error-code %d):\
\"%s\"", curl_errornr, curlerror);
had_err = -1;
}
if (!had_err)
{
/* Die Hit-DNA steht zwischen dem <GBSeq_sequence> und dem
</GBSeq_sequence> XML-Tag, Zeiger auf das < Zeichen von
<GBSeq_sequence> */
seq_pos = strstr(memorystruct.memory, "<GBSeq_sequence>");
if (!seq_pos)
{
gt_error_set(err,
"an error occurred while retrieving sequence-information\
with the following request: \"%s\"", http_adr_ptr);
had_err = -1;
}
static int layout_tracks(void *key, void *value, void *data,
GtError *err)
{
unsigned long i,
max = 50;
GtTrack *track = NULL;
GtLayoutTraverseInfo *lti = (GtLayoutTraverseInfo*) data;
GtArray *list = (GtArray*) value;
GtStr *gt_track_key;
GtBlock *block;
int had_err = 0;
bool split = true;
double tmp = 50;
gt_assert(list);
/* to get a deterministic layout, we sort the GtBlocks for each type */
if (lti->layout->block_ordering_func) {
gt_array_sort_stable_with_data(list, blocklist_block_compare,
lti->layout);
}
/* XXX: get first block for track property lookups, this should be reworked
to allow arbitrary track keys! */
block = *(GtBlock**) gt_array_get(list, 0);
gt_track_key = gt_str_new_cstr((char*) key);
/* obtain default settings*/
if (gt_style_get_bool(lti->layout->style, "format", "split_lines", &split,
NULL, err) == GT_STYLE_QUERY_ERROR) {
had_err = 1;
}
if (!had_err) {
if (gt_style_get_num(lti->layout->style,
"format", "max_num_lines",
&tmp, NULL, err) == GT_STYLE_QUERY_ERROR) {
had_err = 1;
}
}
/* obtain track-specific settings, should be changed to query arbitrary
track keys! */
if (!had_err) {
if (gt_style_get_bool(lti->layout->style, gt_block_get_type(block),
"split_lines", &split, NULL,
err) == GT_STYLE_QUERY_ERROR) {
had_err = 1;
}
}
if (!had_err) {
if (gt_style_get_num(lti->layout->style, gt_block_get_type(block),
"max_num_lines", &tmp, NULL,
err) == GT_STYLE_QUERY_ERROR) {
had_err = 1;
}
}
if (!had_err) {
max = (unsigned long) tmp;
track = gt_track_new(gt_track_key, max, split,
gt_line_breaker_captions_new(lti->layout,
lti->layout->width,
lti->layout->style));
lti->layout->nof_tracks++;
for (i = 0; !had_err && i < gt_array_size(list); i++) {
block = *(GtBlock**) gt_array_get(list, i);
had_err = gt_track_insert_block(track, block, err);
}
}
if (!had_err) {
gt_hashmap_add(lti->layout->tracks, gt_cstr_dup(gt_str_get(gt_track_key)),
track);
}
else
{
gt_track_delete(track);
}
gt_str_delete(gt_track_key);
return had_err;
}
static int hmmsearch_process_coarse_hits(
char *table_filename,
GtCondenseq *ces,
GtCondenseqHmmsearchArguments *arguments,
GtLogger *logger,
GtError *err) {
int had_err = 0;
GtStr *line = gt_str_new();
FILE *table = NULL;
GtSplitter *splitter = gt_splitter_new();
GtStr *query = gt_str_new(),
*fine_fasta_filename = gt_str_new_cstr("condenseq");
GtRBTree *sequences = NULL;
GtUword filecount = (GtUword) 1;
unsigned int querycount = 0;
const GtUword fine_fasta_name_length = gt_str_length(fine_fasta_filename);
const GtUword table_name_length = gt_str_length(arguments->outtable_filename);
table = gt_xfopen(table_filename, "r");
sequences = gt_rbtree_new(hmmsearch_cmp_seqnum,
hmmsearch_tree_free_node, NULL);
while (!had_err && gt_str_read_next_line(line, table) == 0) {
char *c_line = gt_str_get(line);
GtUword uid;
const GtUword target_column = 0,
query_column = (GtUword) 3;
if (c_line[0] != '#') {
gt_splitter_split_non_empty(splitter, c_line, gt_str_length(line), ' ');
gt_assert(gt_splitter_size(splitter) == (GtUword) 23);
if (sscanf(gt_splitter_get_token(splitter, target_column),
GT_WU, &uid) != 1) {
gt_error_set(err, "couldn't parse target number: %s",
gt_splitter_get_token(splitter, target_column));
had_err = -1;
}
if (gt_str_length(query) == 0 ||
strcmp(gt_str_get(query),
gt_splitter_get_token(splitter, query_column)) != 0) {
gt_str_set(query, gt_splitter_get_token(splitter, query_column));
gt_logger_log(logger, "new query: %s", gt_str_get(query));
querycount++;
}
if (!had_err && querycount == arguments->max_queries) {
hmmsearch_create_fine_fas(fine_fasta_filename, sequences, ces);
if (table_name_length != 0)
gt_str_append_uword(arguments->outtable_filename, filecount++);
had_err =
hmmsearch_call_fine_search(table_name_length != 0 ?
arguments->outtable_filename :
NULL,
gt_str_get(fine_fasta_filename),
gt_str_get(arguments->hmmsearch_path),
gt_str_get(arguments->hmm),
logger, err);
gt_rbtree_clear(sequences);
gt_str_set_length(fine_fasta_filename, fine_fasta_name_length);
if (table_name_length != 0)
gt_str_set_length(arguments->outtable_filename, table_name_length);
querycount = 0;
}
if (!had_err) {
if (gt_condenseq_each_redundant_seq(ces, uid,
hmmsearch_process_seq,
sequences, err) == 0) {
had_err = -1;
}
}
gt_splitter_reset(splitter);
}
gt_str_reset(line);
}
gt_splitter_delete(splitter);
gt_str_delete(line);
gt_str_delete(query);
gt_xfclose(table);
if (!had_err) {
hmmsearch_create_fine_fas(fine_fasta_filename, sequences, ces);
if (table_name_length != 0)
gt_str_append_uword(arguments->outtable_filename, filecount++);
had_err =
hmmsearch_call_fine_search(table_name_length != 0 ?
arguments->outtable_filename :
NULL,
gt_str_get(fine_fasta_filename),
gt_str_get(arguments->hmmsearch_path),
gt_str_get(arguments->hmm),
logger, err);
}
gt_log_log("created " GT_WU " files", filecount);
gt_rbtree_delete(sequences);
gt_str_delete(fine_fasta_filename);
return had_err;
}
int gt_block_unit_test(GtError *err)
{
GtRange r1, r2, r_temp, b_range;
GtStrand s;
GtGenomeNode *gn1, *gn2;
GtElement *e1, *e2;
double height;
GtBlock *b;
GtStr *seqid, *caption1, *caption2;
int had_err = 0;
GtStyle *sty;
GtError *testerr;
gt_error_check(err);
seqid = gt_str_new_cstr("seqid");
caption1 = gt_str_new_cstr("foo");
caption2 = gt_str_new_cstr("bar");
testerr = gt_error_new();
r1.start = 10UL;
r1.end = 50UL;
r2.start = 40UL;
r2.end = 50UL;
gn1 = gt_feature_node_new(seqid, gt_ft_gene, r1.start, r1.end,
GT_STRAND_FORWARD);
gn2 = gt_feature_node_new(seqid, gt_ft_exon, r2.start, r2.end,
GT_STRAND_FORWARD);
e1 = gt_element_new((GtFeatureNode*) gn1);
e2 = gt_element_new((GtFeatureNode*) gn2);
b = gt_block_new();
/* test gt_block_insert_elements */
gt_ensure((0UL == gt_block_get_size(b)));
gt_block_insert_element(b, (GtFeatureNode*) gn1);
gt_ensure((1UL == gt_block_get_size(b)));
gt_block_insert_element(b, (GtFeatureNode*) gn2);
gt_ensure((2UL == gt_block_get_size(b)));
/* test gt_block_set_range & gt_block_get_range */
r_temp = gt_range_join(&r1, &r2);
gt_block_set_range(b, r_temp);
b_range = gt_block_get_range(b);
gt_ensure((0 == gt_range_compare(&b_range, &r_temp)));
gt_ensure((1 == gt_range_compare(&r2, &r_temp)));
/* tests gt_block_set_caption & gt_block_get_caption */
gt_block_set_caption(b, caption1);
gt_ensure((0 == gt_str_cmp(gt_block_get_caption(b), caption1)));
gt_ensure((0 != gt_str_cmp(gt_block_get_caption(b), caption2)));
/* tests gt_block_set_strand & gt_block_get_range */
s = gt_block_get_strand(b);
gt_ensure((GT_STRAND_UNKNOWN == s));
gt_block_set_strand(b, GT_STRAND_FORWARD);
s = gt_block_get_strand(b);
gt_ensure((GT_STRAND_FORWARD == s));
/* test gt_block_get_max_height() */
sty = gt_style_new(err);
gt_ensure(gt_block_get_max_height(b, &height, sty, err) == 0);
gt_ensure(!gt_error_is_set(testerr));
gt_ensure(height == BAR_HEIGHT_DEFAULT);
gt_style_set_num(sty, "exon", "bar_height", 42);
gt_ensure(gt_block_get_max_height(b, &height, sty, err) == 0);
gt_ensure(!gt_error_is_set(testerr));
gt_ensure(height == 42);
gt_style_set_num(sty, "gene", "bar_height", 23);
gt_ensure(gt_block_get_max_height(b, &height, sty, err) == 0);
gt_ensure(!gt_error_is_set(testerr));
gt_ensure(height == 42);
gt_style_unset(sty, "exon", "bar_height");
gt_ensure(gt_block_get_max_height(b, &height, sty, err) == 0);
gt_ensure(!gt_error_is_set(testerr));
gt_ensure(height == 23);
gt_str_delete(caption2);
gt_str_delete(seqid);
gt_element_delete(e1);
gt_element_delete(e2);
gt_block_delete(b);
gt_style_delete(sty);
gt_error_delete(testerr);
gt_genome_node_delete(gn1);
gt_genome_node_delete(gn2);
return had_err;
}
int gt_track_unit_test(GtError *err)
{
int had_err = 0;
GtBlock *b[4];
GtRange r[4];
GtTrack *track;
GtGenomeNode *parent[4], *gn[4];
GtStr *title;
double height, tmp;
GtStyle *sty;
unsigned long i;
GtLineBreaker *lb;
double t_rest = 0,
l_rest = 0;
gt_error_check(err);
title = gt_str_new_cstr("test");
r[0].start=100UL;
r[0].end=1000UL;
r[1].start=1001UL;
r[1].end=1500UL;
r[2].start=700UL;
r[2].end=1200UL;
r[3].start=10UL;
r[3].end=200UL;
for (i=0; i<4; i++)
{
parent[i] = gt_feature_node_new(title, gt_ft_gene, r[i].start, r[i].end,
GT_STRAND_FORWARD);
gn[i] = gt_feature_node_new(title, gt_ft_exon, r[i].start, r[i].end,
GT_STRAND_FORWARD);
gt_feature_node_add_child((GtFeatureNode*) parent[i],
(GtFeatureNode*) gn[i]);
gt_feature_node_add_attribute((GtFeatureNode*) parent[i], GT_GFF_NAME,
"parent");
gt_feature_node_add_attribute((GtFeatureNode*) gn[i], GT_GFF_NAME, "child");
}
for (i=0; i<4; i++)
{
b[i] = gt_block_new();
gt_block_set_range(b[i], r[i]);
gt_block_insert_element(b[i], (GtFeatureNode*) parent[i]);
gt_block_insert_element(b[i], (GtFeatureNode*) gn[i]);
}
lb = gt_line_breaker_bases_new();
sty = gt_style_new(err);
if (gt_style_get_num(sty, "format", "track_caption_font_size", &tmp,
NULL, err) == GT_STYLE_QUERY_NOT_SET) {
tmp = TEXT_SIZE_DEFAULT;
}
t_rest += tmp;
if (gt_style_get_num(sty, "format", "track_caption_space", &tmp,
NULL, err) == GT_STYLE_QUERY_NOT_SET) {
tmp = CAPTION_BAR_SPACE_DEFAULT;
}
t_rest += tmp;
if (gt_style_get_num(sty, "format", "track_vspace", &tmp,
NULL, err) == GT_STYLE_QUERY_NOT_SET) {
tmp = TRACK_VSPACE_DEFAULT;
}
t_rest += tmp;
if (gt_style_get_num(sty, "format", "bar_vspace", &l_rest,
NULL, err) == GT_STYLE_QUERY_NOT_SET) {
l_rest = BAR_VSPACE_DEFAULT;
}
track = gt_track_new(title, GT_UNDEF_ULONG, true, lb);
gt_ensure(had_err, track);
gt_ensure(had_err, gt_track_get_title(track) == title);
gt_ensure(had_err, gt_track_get_number_of_lines(track) == 0);
gt_ensure(had_err, gt_track_get_height(track, &height, sty, err) == 0);
gt_ensure(had_err, height == t_rest);
gt_ensure(had_err, !gt_error_is_set(err));
gt_ensure(had_err, gt_track_insert_block(track, b[0], err) == 0);
gt_ensure(had_err, !gt_error_is_set(err));
gt_ensure(had_err, gt_track_get_number_of_lines(track) == 1);
gt_ensure(had_err, gt_track_get_height(track, &height, sty, err) == 0);
gt_ensure(had_err, height == t_rest + l_rest + BAR_HEIGHT_DEFAULT);
gt_ensure(had_err, !gt_error_is_set(err));
gt_ensure(had_err, gt_track_insert_block(track, b[1], err) == 0);
gt_ensure(had_err, !gt_error_is_set(err));
gt_ensure(had_err, gt_track_get_number_of_lines(track) == 1);
gt_ensure(had_err, gt_track_get_height(track, &height, sty, err) == 0);
gt_ensure(had_err, height == t_rest + l_rest + BAR_HEIGHT_DEFAULT);
gt_ensure(had_err, !gt_error_is_set(err));
gt_ensure(had_err, gt_track_insert_block(track, b[2], err) == 0);
gt_ensure(had_err, !gt_error_is_set(err));
gt_ensure(had_err, gt_track_get_number_of_lines(track) == 2);
gt_ensure(had_err, gt_track_insert_block(track, b[3], err) == 0);
gt_ensure(had_err, !gt_error_is_set(err));
gt_ensure(had_err, gt_track_get_number_of_lines(track) == 2);
gt_ensure(had_err, gt_track_get_height(track, &height, sty, err) == 0);
gt_ensure(had_err, height == t_rest + 2*(l_rest + BAR_HEIGHT_DEFAULT));
gt_ensure(had_err, !gt_error_is_set(err));
gt_style_set_num(sty, "exon", "bar_height", 42);
gt_ensure(had_err, gt_track_get_height(track, &height, sty, err) == 0);
gt_ensure(had_err, height == t_rest + 2*(l_rest+42));
gt_ensure(had_err, !gt_error_is_set(err));
gt_style_set_num(sty, "gene", "bar_height", 23);
gt_ensure(had_err, gt_track_get_height(track, &height, sty, err) == 0);
gt_ensure(had_err, height == t_rest + 2*(l_rest+42));
gt_ensure(had_err, !gt_error_is_set(err));
gt_style_unset(sty, "exon", "bar_height");
gt_ensure(had_err, gt_track_get_height(track, &height, sty, err) == 0);
gt_ensure(had_err, height == t_rest + 2*(l_rest+23));
gt_ensure(had_err, !gt_error_is_set(err));
gt_style_unset(sty, "gene", "bar_height");
gt_style_set_num(sty, "format", "bar_height", 99);
gt_ensure(had_err, gt_track_get_height(track, &height, sty, err) == 0);
gt_ensure(had_err, height == t_rest + 2*(l_rest+99));
gt_ensure(had_err, !gt_error_is_set(err));
gt_ensure(had_err, gt_track_get_number_of_discarded_blocks(track) == 0);
gt_track_delete(track);
gt_str_delete(title);
gt_style_delete(sty);
for (i=0; i<4; i++)
{
gt_block_delete(b[i]);
gt_genome_node_delete(parent[i]);
}
return had_err;
}
static void make_sequence_region(GtHashmap *sequence_regions,
GtStr *sequenceid,
GthRegionFactory *srf,
GthInput *input,
GtUword filenum,
GtUword seqnum)
{
GtUword offset_is_defined = false;
GtRange range, descrange;
GtGenomeNode *sr = NULL;
gt_assert(sequence_regions && sequenceid && srf && input);
if (gth_input_use_substring_spec(input)) {
range.start = gth_input_genomic_substring_from(input);
range.end = gth_input_genomic_substring_to(input);
}
else {
range = gth_input_get_relative_genomic_range(input, filenum, seqnum);
}
if (srf->use_desc_ranges) {
GtStr *description = gt_str_new();
gth_input_get_genomic_description(input, description, filenum, seqnum);
if (!gt_parse_description_range(gt_str_get(description), &descrange))
offset_is_defined = true;
gt_str_delete(description);
}
if (offset_is_defined)
range = gt_range_offset(&range, descrange.start);
else
range = gt_range_offset(&range, 1); /* 1-based */
if (!gt_str_length(sequenceid) ||
(gt_cstr_table_get(srf->used_seqids, gt_str_get(sequenceid)) &&
!offset_is_defined)) {
/* sequenceid is empty or exists already (and no offset has been parsed)
-> make one up */
GtStr *seqid;
char *base;
base = gt_basename(gth_input_get_genomic_filename(input, filenum));
seqid = gt_str_new_cstr(base);
gt_free(base);
gt_str_append_char(seqid, '|');
gt_str_append_uword(seqid, seqnum + 1); /* 1-based */
seqid_store_add(srf->seqid_store, filenum, seqnum, seqid, GT_UNDEF_UWORD);
gt_assert(!gt_cstr_table_get(srf->used_seqids, gt_str_get(seqid)));
gt_cstr_table_add(srf->used_seqids, gt_str_get(seqid));
sr = gt_region_node_new(seqid_store_get(srf->seqid_store, filenum, seqnum),
range.start, range.end);
gt_hashmap_add(sequence_regions,
(void*) gt_cstr_table_get(srf->used_seqids,
gt_str_get(seqid)),
sr);
gt_str_delete(seqid);
}
else {
/* sequenceid does not exists already (or an offset has been parsed)
-> use this one */
if (!gt_cstr_table_get(srf->used_seqids, gt_str_get(sequenceid))) {
/* no sequence region with this id exists -> create one */
gt_cstr_table_add(srf->used_seqids, gt_str_get(sequenceid));
seqid_store_add(srf->seqid_store, filenum, seqnum, sequenceid,
offset_is_defined ? descrange.start : GT_UNDEF_UWORD);
sr = gt_region_node_new(seqid_store_get(srf->seqid_store, filenum,
seqnum), range.start, range.end);
gt_hashmap_add(sequence_regions,
(void*) gt_cstr_table_get(srf->used_seqids,
gt_str_get(sequenceid)),
sr);
}
else {
GtRange prev_range, new_range;
/* sequence region with this id exists already -> modify range */
sr = gt_hashmap_get(sequence_regions, gt_str_get(sequenceid));
gt_assert(sr);
prev_range = gt_genome_node_get_range(sr);
new_range = gt_range_join(&prev_range, &range);
gt_genome_node_set_range(sr, &new_range);
seqid_store_add(srf->seqid_store, filenum, seqnum, sequenceid,
offset_is_defined ? descrange.start : GT_UNDEF_UWORD);
}
}
gt_assert(sr);
}