/* Formats a given position number for short display in the ruler. */
void gt_format_ruler_label(char *txt, GtUword pos,
const char *unitstr, size_t buflen)
{
double fpos;
int logval;
GtStr *formatstring;
gt_assert(txt);
logval = (int) floor(log10(pos));
formatstring = gt_str_new_cstr("%.");
if (pos >= 1000000000)
{
fpos = (double) pos / 1000000000;
while (pos % 10 == 0)
{
pos /= 10;
logval--;
}
/*@ignore@*/
gt_str_append_ulong(formatstring, (GtUword) logval);
gt_str_append_cstr(formatstring, "fG%s");
(void) snprintf(txt, buflen, gt_str_get(formatstring), fpos, unitstr);
/*@end@*/
}
else if (pos >= 1000000)
{
fpos = (double) pos / 1000000;
while (pos % 10 == 0)
{
pos /= 10;
logval--;
}
/*@ignore@*/
gt_str_append_ulong(formatstring, (GtUword) logval);
gt_str_append_cstr(formatstring, "fM%s");
(void) snprintf(txt, buflen, gt_str_get(formatstring), fpos, unitstr);
/*@end@*/
}
else if (pos >= 1000)
{
fpos = (double) pos / 1000;
while (pos % 10 == 0)
{
pos /= 10;
logval--;
}
/*@ignore@*/
gt_str_append_ulong(formatstring, (GtUword) logval);
gt_str_append_cstr(formatstring, "fk%s");
(void) snprintf(txt, buflen, gt_str_get(formatstring), fpos, unitstr);
/*@end@*/
} else {
/*@ignore@*/
(void) snprintf(txt, buflen, " "GT_WU"%s", pos, unitstr);
/*@end@*/
}
gt_str_delete(formatstring);
}
void gt_gff3_output_leading_str(GtFeatureNode *fn, GtStr *outstr)
{
GtGenomeNode *gn;
gt_assert(fn && outstr);
gn = (GtGenomeNode*) fn;
gt_str_append_str(outstr, gt_genome_node_get_seqid(gn));
gt_str_append_char(outstr, '\t');
gt_str_append_cstr(outstr, gt_feature_node_get_source(fn));
gt_str_append_char(outstr, '\t');
gt_str_append_cstr(outstr, gt_feature_node_get_type(fn));
gt_str_append_char(outstr, '\t');
gt_str_append_ulong(outstr, gt_genome_node_get_start(gn));
gt_str_append_char(outstr, '\t');
gt_str_append_ulong(outstr, gt_genome_node_get_end(gn));
gt_str_append_char(outstr, '\t');
if (gt_feature_node_score_is_defined(fn)) {
char buf[BUFSIZ];
(void) snprintf(buf, BUFSIZ, "%.3g", gt_feature_node_get_score(fn));
gt_str_append_cstr(outstr, buf);
} else
gt_str_append_char(outstr, '.');
gt_str_append_char(outstr, '\t');
gt_str_append_char(outstr, GT_STRAND_CHARS[gt_feature_node_get_strand(fn)]);
gt_str_append_char(outstr, '\t');
gt_str_append_char(outstr, GT_PHASE_CHARS[gt_feature_node_get_phase(fn)]);
gt_str_append_char(outstr, '\t');
}
static int gff3_visitor_region_node(GtNodeVisitor *nv, GtRegionNode *rn,
GT_UNUSED GtError *err)
{
GtGFF3Visitor *gff3_visitor;
gt_error_check(err);
gff3_visitor = gff3_visitor_cast(nv);
gt_assert(nv && rn);
gff3_version_string(nv);
if (!gff3_visitor->outstr) {
gt_file_xprintf(gff3_visitor->outfp, "%s %s "GT_WU" "GT_WU"\n",
GT_GFF_SEQUENCE_REGION,
gt_str_get(gt_genome_node_get_seqid((GtGenomeNode*) rn)),
gt_genome_node_get_start((GtGenomeNode*) rn),
gt_genome_node_get_end((GtGenomeNode*) rn));
} else {
gt_str_append_cstr(gff3_visitor->outstr, GT_GFF_SEQUENCE_REGION);
gt_str_append_cstr(gff3_visitor->outstr, " ");
gt_str_append_cstr(gff3_visitor->outstr,
gt_str_get(gt_genome_node_get_seqid((GtGenomeNode*) rn)));
gt_str_append_char(gff3_visitor->outstr, ' ');
gt_str_append_ulong(gff3_visitor->outstr,
gt_genome_node_get_start((GtGenomeNode*) rn));
gt_str_append_char(gff3_visitor->outstr, ' ');
gt_str_append_ulong(gff3_visitor->outstr,
gt_genome_node_get_end((GtGenomeNode*) rn));
gt_str_append_char(gff3_visitor->outstr, '\n');
}
return 0;
}
static void set_gff3_target_attribute(GthSA *sa, bool md5ids)
{
gt_assert(sa && !sa->gff3_target_attribute);
sa->gff3_target_attribute = gt_str_new();
if (md5ids) {
gt_assert(sa->ref_md5);
gt_str_append_cstr(sa->gff3_target_attribute, GT_MD5_SEQID_PREFIX);
gt_str_append_str(sa->gff3_target_attribute, sa->ref_md5);
gt_str_append_char(sa->gff3_target_attribute, ':');
}
gt_gff3_escape(sa->gff3_target_attribute, gt_str_get(sa->ref_id),
gt_str_length(sa->ref_id));
gt_str_append_char(sa->gff3_target_attribute, ' ');
gt_str_append_ulong(sa->gff3_target_attribute,
gth_sa_referencecutoff_start(sa) + 1); /* XXX: use
reference
dpstartpos */
gt_str_append_char(sa->gff3_target_attribute, ' ');
gt_str_append_ulong(sa->gff3_target_attribute,
gth_sa_ref_total_length(sa) - /* XXX */
gth_sa_referencecutoff_end(sa));
gt_str_append_char(sa->gff3_target_attribute, ' ');
if (sa->ref_strand_forward) {
gt_str_append_char(sa->gff3_target_attribute,
GT_STRAND_CHARS[GT_STRAND_FORWARD]);
}
else {
gt_str_append_char(sa->gff3_target_attribute,
GT_STRAND_CHARS[GT_STRAND_REVERSE]);
}
}
static void construct_description(GtStr *description, const char *type,
GtUword counter, bool join,
bool translate, GtStr *seqid,
GtStrArray *target_ids)
{
gt_assert(!gt_str_length(description));
gt_str_append_cstr(description, type);
gt_str_append_char(description, '_');
gt_str_append_ulong(description, counter);
if (join)
gt_str_append_cstr(description, " (joined)");
if (translate)
gt_str_append_cstr(description, " (translated)");
if (seqid) {
gt_assert(gt_str_length(seqid));
gt_str_append_cstr(description, " [seqid ");
gt_str_append_str(description, seqid);
gt_str_append_char(description, ']');
}
if (target_ids && gt_str_array_size(target_ids)) {
GtUword i;
gt_str_append_cstr(description, " [target IDs ");
gt_str_append_cstr(description, gt_str_array_get(target_ids, 0));
for (i = 1; i < gt_str_array_size(target_ids); i++) {
gt_str_append_char(description, ',');
gt_str_append_cstr(description, gt_str_array_get(target_ids, i));
}
gt_str_append_char(description, ']');
}
}
static void close_output_files(Store_in_subset_file_data
*store_in_subset_file_data)
{
unsigned long i;
GtStr *buf;
buf = gt_str_new();
for (i = 0; i < store_in_subset_file_data->num_of_subset_files; i++) {
if (store_in_subset_file_data->subset_files[i]) {
if (store_in_subset_file_data->gthsplitinfo->showverbose) {
gt_str_reset(buf);
gt_str_append_cstr(buf, "split file created: ");
gt_str_append_str(buf, store_in_subset_file_data->subset_filenames[i]);
gt_str_append_cstr(buf, " (size=");
gt_str_append_ulong(buf,
store_in_subset_file_data->subset_file_sa_counter[i]);
gt_str_append_cstr(buf, ")");
store_in_subset_file_data->gthsplitinfo->showverbose(gt_str_get(buf));
}
gt_assert(store_in_subset_file_data->subset_filenames[i]);
/* put XML trailer in file before closing it */
gth_xml_show_trailer(true, store_in_subset_file_data->subset_files[i]);
gt_file_delete(store_in_subset_file_data->subset_files[i]);
gt_str_delete(store_in_subset_file_data->subset_filenames[i]);
store_in_subset_file_data->subset_files[i] = NULL;
store_in_subset_file_data->subset_file_sa_counter[i] = 0;
}
}
gt_str_delete(buf);
}
static int gt_ltrdigest_pdom_visitor_attach_hit(GtLTRdigestPdomVisitor *lv,
GtHMMERModelHit *modelhit,
GtHMMERSingleHit *singlehit)
{
GT_UNUSED GtUword i;
GtGenomeNode *gf;
int had_err = 0;
GtRange rrng;
gt_assert(lv && singlehit);
rrng = gt_ltrdigest_pdom_visitor_coords(lv, singlehit);
if (gt_array_size(singlehit->chains) > 0 || lv->output_all_chains) {
char buf[32];
gf = gt_feature_node_new(gt_genome_node_get_seqid((GtGenomeNode*)
lv->ltr_retrotrans),
gt_ft_protein_match,
rrng.start,
rrng.end,
singlehit->strand);
gt_genome_node_add_user_data((GtGenomeNode*) gf, "pdom_alignment",
gt_str_ref(singlehit->alignment),
(GtFree) gt_str_delete);
gt_genome_node_add_user_data((GtGenomeNode*) gf, "pdom_aaseq",
gt_str_ref(singlehit->aastring),
(GtFree) gt_str_delete);
gt_feature_node_set_source((GtFeatureNode*) gf, lv->tag);
gt_feature_node_set_score((GtFeatureNode*) gf, (float) singlehit->evalue);
(void) snprintf(buf, (size_t) 32, "%d", (int) singlehit->frame);
gt_feature_node_add_attribute((GtFeatureNode*) gf,
"reading_frame", buf);
if (modelhit->modelname != NULL) {
gt_feature_node_add_attribute((GtFeatureNode*) gf, "name",
modelhit->modelname);
}
if (gt_array_size(singlehit->chains) > 1UL && lv->output_all_chains) {
GtStr *buffer;
GtUword j;
gt_assert(singlehit->chains != NULL);
buffer = gt_str_new();
for (j = 0UL; j < gt_array_size(singlehit->chains); j++) {
gt_str_append_cstr(buffer, modelhit->modelname);
gt_str_append_char(buffer, ':');
gt_str_append_ulong(buffer,
*(GtUword*) gt_array_get(singlehit->chains, j));
if (j != gt_array_size(singlehit->chains) - 1) {
gt_str_append_char(buffer, ',');
}
}
gt_feature_node_set_attribute((GtFeatureNode*) gf, "chains",
gt_str_get(buffer));
gt_str_delete(buffer);
}
gt_feature_node_add_child(lv->ltr_retrotrans, (GtFeatureNode*) gf);
}
gt_array_delete(singlehit->chains);
singlehit->chains = NULL;
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 void* test_symbol(GT_UNUSED void *data)
{
GtStr *symbol;
GtUword i;
symbol = gt_str_new();
for (i = 0; i < NUMBER_OF_SYMBOLS; i++) {
gt_str_reset(symbol);
gt_str_append_ulong(symbol, gt_rand_max(MAX_SYMBOL));
gt_symbol(gt_str_get(symbol));
gt_assert(!strcmp(gt_symbol(gt_str_get(symbol)), gt_str_get(symbol)));
}
gt_str_delete(symbol);
return NULL;
}
static int gt_seqtranslate_do_translation(GtTranslateArguments *arguments,
const char *sequence,
GtUword length,
const char *desc,
GtStr **translations,
bool rev,
GtError *err)
{
GtTranslator *tr;
GT_UNUSED GtTranslatorStatus trst;
GtCodonIterator *ci;
char translated;
int had_err = 0;
GtStr *str;
unsigned int frame,
i;
ci = gt_codon_iterator_simple_new(sequence, length, err);
tr = gt_translator_new(ci);
trst = gt_translator_next(tr, &translated, &frame, err);
while (trst == GT_TRANSLATOR_OK) {
gt_str_append_char(translations[frame], translated);
trst = gt_translator_next(tr, &translated, &frame, err);
}
gt_codon_iterator_delete(ci);
gt_translator_delete(tr);
if (trst == GT_TRANSLATOR_ERROR)
return -1;
str = gt_str_new();
for (i = 0; i < 3; i++) {
if (gt_str_length(translations[i]) > 0) {
gt_str_append_cstr(str, desc);
gt_str_append_cstr(str, " (");
gt_str_append_ulong(str, i+1);
gt_str_append_cstr(str, rev ? "-" : "+");
gt_str_append_cstr(str, ")");
gt_fasta_show_entry(gt_str_get(str), gt_str_get(translations[i]),
gt_str_length(translations[i]),
arguments->fasta_width, arguments->outfp);
gt_str_reset(translations[i]);
gt_str_reset(str);
}
}
gt_str_delete(str);
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;
}
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;
}
static int store_in_subset_file(void *data, GthSA *sa,
const char *outputfilename, GtError *err)
{
Store_in_subset_file_data *store_in_subset_file_data =
(Store_in_subset_file_data*) data;
double split_determing_percentage = 0.0;
unsigned long filenum;
char filenamesuffix[4];
int had_err = 0;
gt_error_check(err);
/* filter before we do any further processing */
if (gth_sa_filter_filter_sa(store_in_subset_file_data->sa_filter, sa)) {
/* and free it afterwards */
gth_sa_delete(sa);
/* discard */
return 0;
}
/* check whether we got a new output file to process */
if (!store_in_subset_file_data->current_outputfilename) {
store_in_subset_file_data->current_outputfilename =
gt_cstr_dup(outputfilename);
}
else if (strcmp(store_in_subset_file_data->current_outputfilename,
outputfilename)) {
/* close current output files */
close_output_files(store_in_subset_file_data);
gt_free(store_in_subset_file_data->current_outputfilename);
}
/* determine in which file the current sa needs to be put */
switch (store_in_subset_file_data->gthsplitinfo->splitmode) {
case ALIGNMENTSCORE_SPLIT:
split_determing_percentage = gth_sa_score(sa);
strcpy(filenamesuffix, "scr");
break;
case COVERAGE_SPLIT:
split_determing_percentage = gth_sa_coverage(sa);
strcpy(filenamesuffix, "cov");
break;
default: gt_assert(0);
}
gt_assert(split_determing_percentage >= 0.0);
/* XXX: change into an assertion when coverage problem is fixed */
if (split_determing_percentage > 1.0)
split_determing_percentage = 1.0;
if (split_determing_percentage == 1.0)
filenum = store_in_subset_file_data->num_of_subset_files - 1;
else {
filenum = floor(split_determing_percentage * 100.0 /
store_in_subset_file_data->gthsplitinfo->range);
}
gt_assert(filenum < store_in_subset_file_data->num_of_subset_files);
/* make sure the file exists and is open */
if (!store_in_subset_file_data->subset_files[filenum]) {
gt_assert(store_in_subset_file_data->subset_filenames[filenum] == NULL);
store_in_subset_file_data->subset_filenames[filenum] = gt_str_new();
gt_str_append_cstr_nt(store_in_subset_file_data->subset_filenames[filenum],
outputfilename,
gt_file_basename_length(outputfilename));
gt_str_append_char(store_in_subset_file_data->subset_filenames[filenum],
'.');
gt_str_append_cstr(store_in_subset_file_data->subset_filenames[filenum],
filenamesuffix);
gt_str_append_ulong(store_in_subset_file_data->subset_filenames[filenum],
filenum *
store_in_subset_file_data->gthsplitinfo->range);
gt_str_append_char(store_in_subset_file_data->subset_filenames[filenum],
'-');
gt_str_append_ulong(store_in_subset_file_data->subset_filenames[filenum],
(filenum + 1) *
store_in_subset_file_data->gthsplitinfo->range);
gt_str_append_cstr(store_in_subset_file_data->subset_filenames[filenum],
gt_file_mode_suffix(store_in_subset_file_data
->gthsplitinfo->file_mode));
/* if not disabled by -force, check if file already exists */
if (!store_in_subset_file_data->gthsplitinfo->force) {
store_in_subset_file_data->subset_files[filenum] =
gt_file_open(store_in_subset_file_data->gthsplitinfo->file_mode,
gt_str_get(store_in_subset_file_data
->subset_filenames[filenum]), "r", NULL);
if (store_in_subset_file_data->subset_files[filenum]) {
gt_error_set(err, "file \"%s\" exists already. use option -%s to "
"overwrite", gt_str_get(store_in_subset_file_data
->subset_filenames[filenum]),
GT_FORCE_OPT_CSTR);
had_err = -1;
}
}
if (!had_err) {
/* open split file for writing */
store_in_subset_file_data->subset_files[filenum] =
gt_file_xopen_file_mode(store_in_subset_file_data->gthsplitinfo
->file_mode,
gt_str_get(store_in_subset_file_data
->subset_filenames[filenum]), "w");
/* store XML header in file */
gth_xml_show_leader(true,
store_in_subset_file_data->subset_files[filenum]);
}
}
/* put it there */
if (!had_err) {
gth_xml_inter_sa_visitor_set_outfp(store_in_subset_file_data->sa_visitor,
store_in_subset_file_data
->subset_files[filenum]);
gth_sa_visitor_visit_sa(store_in_subset_file_data->sa_visitor, sa);
}
/* adjust counter */
if (!had_err)
store_in_subset_file_data->subset_file_sa_counter[filenum]++;
/* and free it afterwards */
gth_sa_delete(sa);
return had_err;
}
static int split_fasta_file(const char *filename, unsigned long max_filesize,
bool force, GtError *err)
{
GtFile *srcfp = NULL, *destfp = NULL;
GtStr *destfilename = NULL;
unsigned long filenum = 0, bytecount = 0, separator_pos;
int read_bytes, had_err = 0;
char buf[BUFSIZ];
gt_error_check(err);
gt_assert(filename && max_filesize);
/* open source file */
srcfp = gt_file_xopen(filename, "r");
gt_assert(srcfp);
/* read start characters */
if ((read_bytes = gt_file_xread(srcfp, buf, BUFSIZ)) == 0) {
gt_error_set(err, "file \"%s\" is empty", filename);
had_err = -1;
}
bytecount += read_bytes;
/* make sure the file is in fasta format */
if (!had_err && buf[0] != '>') {
gt_error_set(err, "file is not in FASTA format");
had_err = -1;
}
if (!had_err) {
/* open destination file */
destfilename = gt_str_new();
gt_str_append_cstr_nt(destfilename, filename,
gt_file_basename_length(filename));
gt_str_append_char(destfilename, '.');
gt_str_append_ulong(destfilename, ++filenum);
gt_str_append_cstr(destfilename,
gt_file_mode_suffix(gt_file_mode(srcfp)));
if (!(destfp = gt_outputfile_xopen_forcecheck(gt_str_get(destfilename), "w",
force, err))) {
had_err = -1;
}
if (!had_err)
gt_file_xwrite(destfp, buf, read_bytes);
while (!had_err &&
(read_bytes = gt_file_xread(srcfp, buf, BUFSIZ)) != 0) {
if (bytecount + read_bytes > max_filesize) {
int offset = bytecount < max_filesize ? max_filesize - bytecount : 0;
if ((separator_pos = buf_contains_separator(buf, offset, read_bytes))) {
separator_pos--;
gt_assert(separator_pos < read_bytes);
if (separator_pos)
gt_file_xwrite(destfp, buf, separator_pos);
/* close current file */
gt_file_delete(destfp);
/* open new file */
gt_str_reset(destfilename);
gt_str_append_cstr_nt(destfilename, filename,
gt_file_basename_length(filename));
gt_str_append_char(destfilename, '.');
gt_str_append_ulong(destfilename, ++filenum);
gt_str_append_cstr(destfilename,
gt_file_mode_suffix(gt_file_mode(srcfp)));
if (!(destfp =
gt_outputfile_xopen_forcecheck(gt_str_get(destfilename), "w",
force, err))) {
had_err = -1;
break;
}
bytecount = read_bytes - separator_pos; /* reset */
gt_assert(buf[separator_pos] == '>');
gt_file_xwrite(destfp, buf + separator_pos,
read_bytes - separator_pos);
continue;
}
}
bytecount += read_bytes;
gt_file_xwrite(destfp, buf, read_bytes);
}
}
/* free */
gt_str_delete(destfilename);
/* close current file */
gt_file_delete(destfp);
/* close source file */
gt_file_delete(srcfp);
return had_err;
}
static void make_unique_id_string(GtStr *current_id, GtUword counter)
{
/* name => name.1 */
gt_str_append_char(current_id, '.');
gt_str_append_ulong(current_id, counter);
}
static void make_sequence_region(GtHashmap *sequence_regions,
GtStr *sequenceid,
GthRegionFactory *srf,
GthInput *input,
unsigned long filenum,
unsigned long seqnum)
{
unsigned long 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_ulong(seqid, seqnum + 1); /* 1-based */
seqid_store_add(srf->seqid_store, filenum, seqnum, seqid, GT_UNDEF_ULONG);
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_ULONG);
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_ULONG);
}
}
gt_assert(sr);
}