int gt_merstatistics(const char *inputindex,
GtUword mersize,
GtUword minocc,
GtUword maxocc,
const char *storeindex,
bool storecounts,
bool scanfile,
bool performtest,
GtLogger *logger,
GtError *err)
{
bool haserr = false;
Sequentialsuffixarrayreader *ssar;
gt_error_check(err);
ssar = gt_newSequentialsuffixarrayreaderfromfile(inputindex,
SARR_LCPTAB |
SARR_SUFTAB |
SARR_ESQTAB,
(scanfile && !performtest)
? true : false,
logger,
err);
if (ssar == NULL)
{
haserr = true;
}
if (!haserr)
{
if (enumeratelcpintervals(inputindex,
ssar,
storeindex,
storecounts,
mersize,
minocc,
maxocc,
performtest,
logger,
err) != 0)
{
haserr = true;
}
}
if (ssar != NULL)
{
gt_freeSequentialsuffixarrayreader(&ssar);
}
return haserr ? -1 : 0;
}
int gt_tyr_occratio_func(const char *inputindex,
bool scanfile,
unsigned long minmersize,
unsigned long maxmersize,
GtArrayuint64_t *uniquedistribution,
GtArrayuint64_t *nonuniquedistribution,
GtArrayuint64_t *nonuniquemultidistribution,
GtLogger *logger,
GtError *err)
{
bool haserr = false;
Sequentialsuffixarrayreader *ssar;
gt_error_check(err);
ssar = gt_newSequentialsuffixarrayreaderfromfile(inputindex,
SARR_LCPTAB |
SARR_SUFTAB |
SARR_ESQTAB,
scanfile ? SEQ_scan
: SEQ_mappedboth,
logger,
err);
if (ssar == NULL)
{
haserr = true;
}
if (!haserr)
{
if (computeoccurrenceratio(ssar,
minmersize,
maxmersize,
uniquedistribution,
nonuniquedistribution,
nonuniquemultidistribution,
logger,
err) != 0)
{
haserr = true;
}
}
if (ssar != NULL)
{
gt_freeSequentialsuffixarrayreader(&ssar);
}
return haserr ? -1 : 0;
}
static int callenummaxpairs(const char *indexname,
unsigned int userdefinedleastlength,
bool scanfile,
Processmaxpairs processmaxpairs,
void *processmaxpairsinfo,
GtLogger *logger,
GtError *err)
{
bool haserr = false;
Sequentialsuffixarrayreader *ssar;
gt_error_check(err);
ssar = gt_newSequentialsuffixarrayreaderfromfile(indexname,
SARR_LCPTAB |
SARR_SUFTAB |
SARR_ESQTAB |
SARR_SSPTAB,
scanfile ? SEQ_scan
: SEQ_mappedboth,
logger,
err);
if (ssar == NULL)
{
haserr = true;
}
if (!haserr &&
gt_enumeratemaxpairs(ssar,
gt_encseqSequentialsuffixarrayreader(ssar),
gt_readmodeSequentialsuffixarrayreader(ssar),
userdefinedleastlength,
processmaxpairs,
processmaxpairsinfo,
err) != 0)
{
haserr = true;
}
if (ssar != NULL)
{
gt_freeSequentialsuffixarrayreader(&ssar);
}
return haserr ? -1 : 0;
}
static int gt_readjoiner_cnttest_runner(GT_UNUSED int argc,
GT_UNUSED const char **argv, GT_UNUSED int parsed_args,
void *tool_arguments, GT_UNUSED GtError *err)
{
GtReadjoinerCnttestArguments *arguments = tool_arguments;
GtEncseqLoader *el = NULL;
GtEncseq *reads = NULL;
GtBitsequence *bits = NULL;
GtUword nofreads;
int had_err = 0;
gt_error_check(err);
gt_assert(arguments);
if (arguments->test == GT_READJOINER_CNTTEST_SHOWLIST)
{
GtStr *fn = NULL;
fn = gt_str_clone(arguments->readset);
gt_str_append_cstr(fn, GT_READJOINER_SUFFIX_CNTLIST);
had_err = gt_cntlist_parse(gt_str_get(fn), true, &bits, &nofreads, err);
gt_str_delete(fn);
}
else if (arguments->test == GT_READJOINER_CNTTEST_BRUTEFORCE ||
arguments->test == GT_READJOINER_CNTTEST_KMP)
{
el = gt_encseq_loader_new();
gt_encseq_loader_drop_description_support(el);
gt_encseq_loader_disable_autosupport(el);
if (!arguments->singlestrand)
gt_encseq_loader_mirror(el);
reads = gt_encseq_loader_load(el, gt_str_get(arguments->readset), err);
if (reads == NULL)
had_err = -1;
else
{
gt_rdj_pairwise_exact(GT_OVLFIND_CNT, reads, !arguments->singlestrand,
false, arguments->test == GT_READJOINER_CNTTEST_KMP, 1UL, true,
NULL, NULL, false, NULL, &bits, &nofreads);
}
gt_encseq_delete(reads);
gt_encseq_loader_delete(el);
}
else if (arguments->test == GT_READJOINER_CNTTEST_ESA)
{
Sequentialsuffixarrayreader *ssar = NULL;
GtUword readlength = 0, firstrevcompl = 0;
GtLogger *verbose_logger = gt_logger_new(arguments->verbose,
GT_LOGGER_DEFLT_PREFIX, stderr);
ssar = gt_newSequentialsuffixarrayreaderfromfile(gt_str_get(
arguments->readset), SARR_LCPTAB | SARR_SUFTAB | SARR_SSPTAB,
true, verbose_logger, err);
if (gt_error_is_set(err))
had_err = -1;
else
{
nofreads = gt_encseq_num_of_sequences(ssar->encseq);
if (!arguments->singlestrand)
{
nofreads = GT_DIV2(nofreads);
firstrevcompl = nofreads;
}
GT_INITBITTAB(bits, nofreads);
if (!arguments->singlestrand)
if (gt_encseq_accesstype_get(ssar->encseq) == GT_ACCESS_TYPE_EQUALLENGTH)
readlength = gt_encseq_seqlength(ssar->encseq, 0);
(void)gt_contfind_bottomup(ssar, false, bits, arguments->singlestrand ? 0
: firstrevcompl, readlength);
}
if (ssar != NULL)
gt_freeSequentialsuffixarrayreader(&ssar);
gt_logger_delete(verbose_logger);
}
else
{
gt_assert(false);
}
if (!had_err)
had_err = gt_cntlist_show(bits, nofreads, NULL, false, err);
gt_free(bits);
return had_err;
}