static int encseq_lua_has_description_support(lua_State *L)
{
GtEncseq **encseq;
encseq = check_encseq(L, 1);
lua_pushboolean(L, gt_encseq_has_description_support(*encseq));
return 1;
}
static void gt_seqorder_output(unsigned long seqnum, GtEncseq *encseq)
{
GtEncseqReader *esr;
unsigned long startpos, len, desclen = 0;
const char *desc = NULL;
unsigned long i;
startpos = gt_encseq_seqstartpos(encseq, seqnum);
len = gt_encseq_seqlength(encseq, seqnum);
gt_xfputc(GT_FASTA_SEPARATOR, stdout);
if (gt_encseq_has_description_support(encseq))
{
desc = gt_encseq_description(encseq, &desclen, seqnum);
gt_xfwrite(desc, (size_t)1, (size_t)desclen, stdout);
}
gt_xfputc('\n', stdout);
esr = gt_encseq_create_reader_with_readmode(encseq, GT_READMODE_FORWARD,
startpos);
for (i = 0; i < len; i++)
{
gt_xfputc(gt_encseq_reader_next_decoded_char(esr), stdout);
}
gt_encseq_reader_delete(esr);
gt_xfputc('\n', stdout);
}
static int output_sequence(GtEncseq *encseq, GtEncseqDecodeArguments *args,
const char *filename, GtError *err)
{
GtUword i, j, sfrom, sto;
int had_err = 0;
bool has_desc;
GtEncseqReader *esr;
gt_assert(encseq);
if (!(has_desc = gt_encseq_has_description_support(encseq)))
gt_warning("Missing description support for file %s", filename);
if (strcmp(gt_str_get(args->mode), "fasta") == 0) {
/* specify a single sequence to extract */
if (args->seq != GT_UNDEF_UWORD) {
if (args->seq >= gt_encseq_num_of_sequences(encseq)) {
gt_error_set(err,
"requested sequence "GT_WU" exceeds number of sequences "
"("GT_WU")", args->seq,
gt_encseq_num_of_sequences(encseq));
return -1;
}
sfrom = args->seq;
sto = args->seq + 1;
} else if (args->seqrng.start != GT_UNDEF_UWORD
&& args->seqrng.end != GT_UNDEF_UWORD) {
/* specify a sequence range to extract */
if (args->seqrng.start >= gt_encseq_num_of_sequences(encseq)
|| args->seqrng.end >= gt_encseq_num_of_sequences(encseq)) {
gt_error_set(err,
"range "GT_WU"-"GT_WU" includes a sequence number "
"exceeding the total number of sequences ("GT_WU")",
args->seqrng.start,
args->seqrng.end,
gt_encseq_num_of_sequences(encseq));
return -1;
}
sfrom = args->seqrng.start;
sto = args->seqrng.end + 1;
} else {
/* extract all sequences */
sfrom = 0;
sto = gt_encseq_num_of_sequences(encseq);
}
for (i = sfrom; i < sto; i++) {
GtUword desclen, startpos, len;
char buf[BUFSIZ];
const char *desc = NULL;
/* XXX: maybe make this distinction in the functions via readmode? */
if (!GT_ISDIRREVERSE(args->rm)) {
startpos = gt_encseq_seqstartpos(encseq, i);
len = gt_encseq_seqlength(encseq, i);
if (has_desc) {
desc = gt_encseq_description(encseq, &desclen, i);
} else {
(void) snprintf(buf, BUFSIZ, "sequence "GT_WU"", i);
desclen = strlen(buf);
desc = buf;
}
} else {
startpos = gt_encseq_seqstartpos(encseq, i);
len = gt_encseq_seqlength(encseq,
gt_encseq_num_of_sequences(encseq)-1-i);
startpos = gt_encseq_total_length(encseq)
- (gt_encseq_seqstartpos(encseq,
gt_encseq_num_of_sequences(
encseq)-1-i) + len);
if (has_desc) {
desc = gt_encseq_description(encseq,
&desclen,
gt_encseq_num_of_sequences(encseq)-1-i);
} else {
(void) snprintf(buf, BUFSIZ, "sequence "GT_WU"", i);
desclen = strlen(buf);
desc = buf;
}
}
gt_assert(desc);
/* output description */
gt_xfputc(GT_FASTA_SEPARATOR, stdout);
gt_xfwrite(desc, 1, desclen, stdout);
gt_xfputc('\n', stdout);
/* XXX: make this more efficient by writing in a buffer first and then
showing the result */
if (args->singlechars) {
for (j = 0; j < len; j++) {
gt_xfputc(gt_encseq_get_decoded_char(encseq,
startpos + j,
args->rm),
stdout);
}
} else {
esr = gt_encseq_create_reader_with_readmode(encseq, args->rm, startpos);
for (j = 0; j < len; j++) {
gt_xfputc(gt_encseq_reader_next_decoded_char(esr), stdout);
}
gt_encseq_reader_delete(esr);
}
gt_xfputc('\n', stdout);
}
}
if (strcmp(gt_str_get(args->mode), "concat") == 0) {
GtUword from = 0,
to = gt_encseq_total_length(encseq) - 1;
if (args->rng.start != GT_UNDEF_UWORD && args->rng.end != GT_UNDEF_UWORD) {
if (args->rng.end > to) {
had_err = -1;
gt_error_set(err,
"end of range ("GT_WU") exceeds encoded sequence length "
"("GT_WU")", args->rng.end, to);
}
if (!had_err) {
from = args->rng.start;
to = args->rng.end;
}
}
if (!had_err) {
if (args->singlechars) {
for (j = from; j <= to; j++) {
char cc = gt_encseq_get_decoded_char(encseq, j, args->rm);
if (cc == (char) SEPARATOR)
cc = gt_str_get(args->sepchar)[0];
gt_xfputc(cc, stdout);
}
} else {
esr = gt_encseq_create_reader_with_readmode(encseq, args->rm, from);
if (esr) {
for (j = from; j <= to; j++) {
char cc = gt_encseq_reader_next_decoded_char(esr);
if (cc == (char) SEPARATOR)
cc = gt_str_get(args->sepchar)[0];
gt_xfputc(cc, stdout);
}
gt_encseq_reader_delete(esr);
}
}
gt_xfputc('\n', stdout);
}
}
return had_err;
}
static int gt_seqorder_runner(GT_UNUSED int argc, const char **argv,
int parsed_args, void *tool_arguments, GtError *err)
{
GtSeqorderArguments *arguments = tool_arguments;
int had_err = 0;
GtEncseq *encseq;
GtEncseqLoader *loader;
unsigned long i, nofseqs;
gt_error_check(err);
gt_assert(arguments != NULL);
/* load encseq */
loader = gt_encseq_loader_new();
encseq = gt_encseq_loader_load(loader, argv[parsed_args], err);
if (encseq == NULL)
had_err = -1;
if (had_err == 0 && !gt_encseq_has_description_support(encseq))
gt_warning("%s has no description support", argv[parsed_args]);
if (!had_err)
{
nofseqs = gt_encseq_num_of_sequences(encseq);
if (arguments->invert)
{
for (i = nofseqs; i > 0; i--)
gt_seqorder_output(i - 1, encseq);
}
else if (arguments->shuffle)
{
unsigned long *seqnums;
seqnums = gt_malloc(sizeof (unsigned long) * nofseqs);
gt_seqorder_get_shuffled_seqnums(nofseqs, seqnums);
for (i = 0; i < nofseqs; i++)
gt_seqorder_output(seqnums[i], encseq);
gt_free(seqnums);
}
else
{
GtSuffixsortspace *suffixsortspace;
gt_assert(arguments->sort || arguments->revsort);
suffixsortspace
= gt_suffixsortspace_new(nofseqs,
/* Use iterator over sequence separators:
saves a lot of binary searches */
gt_encseq_seqstartpos(encseq, nofseqs-1),
false,NULL);
gt_seqorder_sort(suffixsortspace, encseq);
if (arguments->sort)
for (i = 0; i < nofseqs; i++)
gt_seqorder_output(gt_encseq_seqnum(encseq,
gt_suffixsortspace_getdirect(suffixsortspace, i)), encseq);
else
for (i = nofseqs; i > 0; i--)
gt_seqorder_output(gt_encseq_seqnum(encseq,
gt_suffixsortspace_getdirect(suffixsortspace, i - 1)), encseq);
gt_suffixsortspace_delete(suffixsortspace, false);
}
}
gt_encseq_loader_delete(loader);
gt_encseq_delete(encseq);
return had_err;
}
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;
}
