static GtUword gt_encseq_col_num_of_files(const GtSeqCol *sc)
{
const GtEncseqCol *esc;
esc = gt_encseq_col_cast(sc);
gt_assert(esc);
return gt_encseq_num_of_files(esc->encseq);
}
GtBUstate_shulen *gt_sfx_multiesashulengthdist_new(const GtEncseq *encseq,
GenomediffInfo *gd_info)
{
GtBUstate_shulen *bustate;
bustate = gt_malloc(sizeof (*bustate));
bustate->encseq = encseq;
bustate->previousbucketlastsuffix = ULONG_MAX;
bustate->idxoffset = 0;
bustate->firstedgefromroot = false;
#ifdef SHUDEBUG
bustate->nextid = 0;
#endif
if (gd_info == NULL)
bustate->unit_info = gt_shu_unit_info_new(encseq);
else
bustate->unit_info = gd_info->unit_info;
bustate->numofdbfiles = gt_encseq_num_of_files(encseq);
#ifdef GENOMEDIFF_PAPER_IMPL
bustate->leafdist
= gt_malloc(sizeof (*bustate->leafdist) * bustate->numofdbfiles);
#endif
bustate->file_to_genome_map = bustate->unit_info->map_files;
if (gd_info == NULL)
bustate->shulengthdist = shulengthdist_new(bustate->numofdbfiles);
else
bustate->shulengthdist = gd_info->shulensums;
bustate->stack = (void *) gt_GtArrayGtBUItvinfo_new_shulen();
return bustate;
}
int gt_multiesa2shulengthdist_print(Sequentialsuffixarrayreader *ssar,
const GtEncseq *encseq,
GtError *err)
{
GtBUstate_shulen *state;
bool haserr = false;
state = gt_malloc(sizeof (*state));
state->numofdbfiles = gt_encseq_num_of_files(encseq);
state->encseq = encseq;
#ifdef GENOMEDIFF_PAPER_IMPL
state->leafdist = gt_malloc(sizeof (*state->leafdist) * state->numofdbfiles);
#endif
#ifdef SHUDEBUG
state->nextid = 0;
#endif
state->shulengthdist = shulengthdist_new(state->numofdbfiles);
if (gt_esa_bottomup_shulen(ssar, state, err) != 0)
{
haserr = true;
}
if (!haserr)
{
shulengthdist_print(NULL,(const uint64_t * const*) state->shulengthdist,
state->numofdbfiles);
}
gt_array2dim_delete(state->shulengthdist);
#ifdef GENOMEDIFF_PAPER_IMPL
gt_free(state->leafdist);
#endif
gt_free(state);
return haserr ? -1 : 0;
}
static int encseq_lua_num_of_files(lua_State *L)
{
GtEncseq **encseq;
encseq = check_encseq(L, 1);
lua_pushnumber(L, gt_encseq_num_of_files(*encseq));
return 1;
}
static GtUword gt_encseq_col_get_sequence_length(const GtSeqCol *sc,
GtUword filenum,
GtUword seqnum)
{
GtEncseqCol *esc;
GtUword encseq_seqnum;
esc = gt_encseq_col_cast(sc);
gt_assert(esc && filenum < gt_encseq_num_of_files(esc->encseq));
encseq_seqnum = gt_encseq_filenum_first_seqnum(esc->encseq, filenum) + seqnum;
return gt_encseq_seqlength(esc->encseq, encseq_seqnum);
}
static const char* gt_encseq_col_get_md5_fingerprint(const GtSeqCol *sc,
GtUword filenum,
GtUword seqnum)
{
GtEncseqCol *esc;
esc = gt_encseq_col_cast(sc);
gt_assert(esc && filenum < gt_encseq_num_of_files(esc->encseq));
return gt_md5_tab_get(esc->md5_tab,
gt_encseq_filenum_first_seqnum(esc->encseq,
filenum) + seqnum);
}
static GtUword gt_encseq_col_num_of_seqs(const GtSeqCol *sc,
GtUword filenum)
{
GtEncseqCol *esc;
/* XXX cache function evaluated values */
esc = gt_encseq_col_cast(sc);
gt_assert(esc && filenum < gt_encseq_num_of_files(esc->encseq));
if (gt_encseq_num_of_files(esc->encseq) == 1 && filenum == 0)
return gt_encseq_num_of_sequences(esc->encseq);
else if (filenum == gt_encseq_num_of_files(esc->encseq) - 1) {
return (gt_encseq_num_of_sequences(esc->encseq)
- gt_encseq_filenum_first_seqnum(esc->encseq, filenum));
} else {
GtUword firstpos, nextpos;
gt_assert(filenum < gt_encseq_num_of_files(esc->encseq) - 1);
firstpos = gt_encseq_filenum_first_seqnum(esc->encseq, filenum);
nextpos = gt_encseq_filenum_first_seqnum(esc->encseq, filenum + 1);
return nextpos - firstpos;
}
}
static int encseq_lua_filestartpos(lua_State *L)
{
GtEncseq **encseq;
GtUword fileno;
encseq = check_encseq(L, 1);
fileno = luaL_checknumber(L, 2);
luaL_argcheck(L, fileno < gt_encseq_num_of_files(*encseq), 2,
"cannot exceed number of files");
lua_pushnumber(L, gt_encseq_filestartpos(*encseq, fileno));
return 1;
}
static char* gt_encseq_col_get_description(const GtSeqCol *sc,
GtUword filenum,
GtUword seqnum)
{
GtEncseqCol *esc;
const char *desc;
GtUword encseq_seqnum, desclen;
esc = gt_encseq_col_cast(sc);
gt_assert(esc && filenum < gt_encseq_num_of_files(esc->encseq));
encseq_seqnum = gt_encseq_filenum_first_seqnum(esc->encseq, filenum) + seqnum;
gt_assert(encseq_seqnum < gt_encseq_num_of_sequences(esc->encseq));
desc = gt_encseq_description(esc->encseq, &desclen, encseq_seqnum);
gt_assert(desc && desclen > 0);
return gt_cstr_dup_nt(desc, desclen);;
}
static char* gt_encseq_col_get_sequence(const GtSeqCol *sc,
GtUword filenum,
GtUword seqnum,
GtUword start,
GtUword end)
{
GtEncseqCol *esc;
char *out;
GtUword encseq_seqnum, startpos;
esc = gt_encseq_col_cast(sc);
gt_assert(esc && filenum < gt_encseq_num_of_files(esc->encseq));
encseq_seqnum = gt_encseq_filenum_first_seqnum(esc->encseq, filenum) + seqnum;
gt_assert(encseq_seqnum < gt_encseq_num_of_sequences(esc->encseq));
gt_assert(start <= end);
startpos = gt_encseq_seqstartpos(esc->encseq, encseq_seqnum);
out = gt_calloc(end - start + 1, sizeof (char));
gt_encseq_extract_decoded(esc->encseq, out, startpos + start, startpos + end);
return out;
}
static int gt_encseq_info_runner(GT_UNUSED int argc, const char **argv,
int parsed_args, void *tool_arguments,
GtError *err)
{
GtEncseqInfoArguments *arguments = tool_arguments;
int had_err = 0;
GtAlphabet *alpha;
const GtUchar *chars;
gt_error_check(err);
gt_assert(arguments);
if (arguments->nomap) {
GtEncseqMetadata *emd = gt_encseq_metadata_new(argv[parsed_args], err);
if (!emd)
had_err = -1;
if (!had_err) {
if (!arguments->noindexname) {
gt_file_xprintf(arguments->outfp, "index name: ");
gt_file_xprintf(arguments->outfp, "%s\n", argv[parsed_args]);
}
gt_file_xprintf(arguments->outfp, "file format version: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_metadata_version(emd));
gt_file_xprintf(arguments->outfp, "64-bit file: ");
gt_file_xprintf(arguments->outfp, "%s\n", gt_encseq_metadata_is64bit(emd)
? "yes"
: "no");
gt_file_xprintf(arguments->outfp, "total length: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_metadata_total_length(emd));
gt_file_xprintf(arguments->outfp, "number of sequences: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_metadata_num_of_sequences(emd));
gt_file_xprintf(arguments->outfp, "number of files: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_metadata_num_of_files(emd));
gt_file_xprintf(arguments->outfp, "length of shortest/longest "
"sequence: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"/"GT_WU"\n",
gt_encseq_metadata_min_seq_length(emd),
gt_encseq_metadata_max_seq_length(emd));
gt_file_xprintf(arguments->outfp, "accesstype: ");
gt_file_xprintf(arguments->outfp, "%s\n",
gt_encseq_access_type_str(gt_encseq_metadata_accesstype(emd)));
alpha = gt_encseq_metadata_alphabet(emd);
chars = gt_alphabet_characters(alpha);
gt_file_xprintf(arguments->outfp, "alphabet size: ");
gt_file_xprintf(arguments->outfp, "%u\n",
gt_alphabet_num_of_chars(alpha));
gt_file_xprintf(arguments->outfp, "alphabet characters: ");
gt_file_xprintf(arguments->outfp, "%.*s", gt_alphabet_num_of_chars(alpha),
(char*) chars);
if (gt_alphabet_is_dna(alpha))
gt_file_xprintf(arguments->outfp, " (DNA)");
if (gt_alphabet_is_protein(alpha))
gt_file_xprintf(arguments->outfp, " (Protein)");
gt_file_xprintf(arguments->outfp, "\n");
if (arguments->show_alphabet) {
GtStr *out = gt_str_new();
gt_alphabet_to_str(alpha, out);
gt_file_xprintf(arguments->outfp, "alphabet definition:\n");
gt_file_xprintf(arguments->outfp, "%s\n", gt_str_get(out));
gt_str_delete(out);
}
}
gt_encseq_metadata_delete(emd);
} else {
GtEncseqLoader *encseq_loader;
GtEncseq *encseq;
encseq_loader = gt_encseq_loader_new();
if (arguments->mirror)
gt_encseq_loader_mirror(encseq_loader);
if (!(encseq = gt_encseq_loader_load(encseq_loader,
argv[parsed_args], err)))
had_err = -1;
if (!had_err) {
const GtStrArray *filenames;
GtUword i;
if (!arguments->noindexname) {
gt_file_xprintf(arguments->outfp, "index name: ");
gt_file_xprintf(arguments->outfp, "%s\n", argv[parsed_args]);
}
gt_file_xprintf(arguments->outfp, "file format version: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n", gt_encseq_version(encseq));
gt_file_xprintf(arguments->outfp, "64-bit file: ");
gt_file_xprintf(arguments->outfp, "%s\n", gt_encseq_is_64_bit(encseq)
? "yes"
: "no");
gt_file_xprintf(arguments->outfp, "total length: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_total_length(encseq));
gt_file_xprintf(arguments->outfp, "compressed size: ");
gt_file_xprintf(arguments->outfp, ""GT_WU" bytes\n",
gt_encseq_sizeofrep(encseq));
gt_file_xprintf(arguments->outfp, "number of sequences: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_num_of_sequences(encseq));
gt_file_xprintf(arguments->outfp, "number of files: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_num_of_files(encseq));
gt_file_xprintf(arguments->outfp, "length of shortest/longest "
"sequence: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"/"GT_WU"\n",
gt_encseq_min_seq_length(encseq),
gt_encseq_max_seq_length(encseq));
filenames = gt_encseq_filenames(encseq);
gt_file_xprintf(arguments->outfp, "original filenames:\n");
for (i = 0; i < gt_str_array_size(filenames); i++) {
gt_file_xprintf(arguments->outfp, "\t%s ("GT_WU" characters)\n",
gt_str_array_get(filenames, i),
(GtUword)
gt_encseq_effective_filelength(encseq, i));
}
alpha = gt_encseq_alphabet(encseq);
chars = gt_alphabet_characters(alpha);
gt_file_xprintf(arguments->outfp, "alphabet size: ");
gt_file_xprintf(arguments->outfp, "%u\n",
gt_alphabet_num_of_chars(alpha));
gt_file_xprintf(arguments->outfp, "alphabet characters: ");
gt_file_xprintf(arguments->outfp, "%.*s", gt_alphabet_num_of_chars(alpha),
(char*) chars);
if (gt_alphabet_is_dna(alpha))
gt_file_xprintf(arguments->outfp, " (DNA)");
if (gt_alphabet_is_protein(alpha))
gt_file_xprintf(arguments->outfp, " (Protein)");
gt_file_xprintf(arguments->outfp, "\n");
if (arguments->show_alphabet) {
GtStr *out = gt_str_new();
gt_alphabet_to_str(alpha, out);
gt_file_xprintf(arguments->outfp, "alphabet definition:\n");
gt_file_xprintf(arguments->outfp, "%s\n", gt_str_get(out));
gt_str_delete(out);
}
gt_file_xprintf(arguments->outfp, "character distribution:\n");
for (i = 0; i < gt_alphabet_num_of_chars(alpha); i++) {
GtUword cc;
cc = gt_encseq_charcount(encseq, gt_alphabet_encode(alpha, chars[i]));
gt_file_xprintf(arguments->outfp, "\t%c: "GT_WU" (%.2f%%)\n",
(char) chars[i],
cc,
(cc /(double) (gt_encseq_total_length(encseq)
- gt_encseq_num_of_sequences(encseq)+1))*100);
}
gt_file_xprintf(arguments->outfp, "number of wildcards: ");
gt_file_xprintf(arguments->outfp, ""GT_WU" ("GT_WU" range(s))\n",
gt_encseq_wildcards(encseq),
gt_encseq_realwildcardranges(encseq));
gt_file_xprintf(arguments->outfp, "number of special characters: ");
gt_file_xprintf(arguments->outfp, ""GT_WU" ("GT_WU" range(s))\n",
gt_encseq_specialcharacters(encseq),
gt_encseq_realspecialranges(encseq));
gt_file_xprintf(arguments->outfp, "length of longest non-special "
"character stretch: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_lengthoflongestnonspecial(encseq));
gt_file_xprintf(arguments->outfp, "accesstype: ");
gt_file_xprintf(arguments->outfp, "%s\n",
gt_encseq_access_type_str(gt_encseq_accesstype_get(encseq)));
gt_file_xprintf(arguments->outfp, "bits used per character: ");
gt_file_xprintf(arguments->outfp, "%f\n",
(double) ((uint64_t) CHAR_BIT *
(uint64_t) gt_encseq_sizeofrep(encseq)) /
(double) gt_encseq_total_length(encseq));
gt_file_xprintf(arguments->outfp, "has special ranges: ");
gt_file_xprintf(arguments->outfp, "%s\n",
gt_encseq_has_specialranges(encseq)
? "yes"
: "no");
gt_file_xprintf(arguments->outfp, "has description support: ");
gt_file_xprintf(arguments->outfp, "%s\n",
gt_encseq_has_description_support(encseq)
? "yes"
: "no");
if (gt_encseq_has_description_support(encseq)) {
gt_file_xprintf(arguments->outfp, "length of longest description: ");
gt_file_xprintf(arguments->outfp, ""GT_WU"\n",
gt_encseq_max_desc_length(encseq));
}
gt_file_xprintf(arguments->outfp, "has multiple sequence support: ");
gt_file_xprintf(arguments->outfp, "%s\n",
gt_encseq_has_multiseq_support(encseq)
? "yes"
: "no");
}
gt_encseq_delete(encseq);
gt_encseq_loader_delete(encseq_loader);
}
return had_err;
}