const char *gt_condenseq_extract_decoded_range(GtCondenseq *condenseq,
GtRange range,
char separator)
{
GtUword length = range.end - range.start + 1,
idx;
const GtUchar *ubuf;
char *buf;
gt_assert(range.start <= range.end);
ubuf = gt_condenseq_extract_encoded_range(condenseq, range);
if (condenseq->buffer == NULL || condenseq->buffsize < length) {
condenseq->buffer = gt_realloc(condenseq->buffer,
sizeof (*condenseq->buffer) * length);
condenseq->buffsize = length;
}
buf = condenseq->buffer;
for (idx = 0; idx < length; ++idx) {
if (ubuf[idx] == SEPARATOR) {
buf[idx] = separator;
}
else {
buf[idx] = gt_alphabet_decode(condenseq->alphabet, ubuf[idx]);
}
}
return buf;
}
void gt_score_matrix_show(const GtScoreMatrix *sm, FILE *fp)
{
unsigned i, j;
gt_assert(sm && fp);
/* show alphabet line */
gt_xfputc(' ', fp);
for (i = 0; i < gt_alphabet_size(sm->alphabet); i++)
fprintf(fp, " %c", gt_alphabet_decode(sm->alphabet, i));
gt_xfputc('\n', fp);
/* show score lines */
for (i = 0; i < gt_alphabet_size(sm->alphabet); i++) {
gt_xfputc(gt_alphabet_decode(sm->alphabet, i), fp);
for (j = 0; j < gt_alphabet_size(sm->alphabet); j++)
fprintf(fp, " %2d", gt_score_matrix_get_score(sm, i, j));
gt_xfputc('\n', fp);
}
}
char gt_wtree_encseq_unmap_decoded(GtWtree *wtree,
GtWtreeSymbol symbol)
{
GtWtreeEncseq *wtree_encseq;
GtUchar encseq_sym = (GtUchar) symbol;
gt_assert((symbol & ((GtUchar) 0)) == 0);
gt_assert(wtree != NULL);
wtree_encseq = gt_wtree_encseq_cast(wtree);
switch (wtree_encseq->alpha_size - encseq_sym) {
case 1:
return (char) SEPARATOR;
case 2:
return gt_alphabet_decode(wtree_encseq->alpha, (GtUchar) WILDCARD);
case 3:
return (char) UNDEFCHAR;
default:
return gt_alphabet_decode(wtree_encseq->alpha, encseq_sym);
}
}
static int alphabet_lua_decode(lua_State *L)
{
GtAlphabet **alpha;
unsigned int code;
char character;
alpha = check_alphabet(L, 1);
code = luaL_checkinteger(L, 2);
/* XXX: too restrictive, does not consider wildcards */
luaL_argcheck(L, code < gt_alphabet_size(*alpha), 2, "invalid code");
character = gt_alphabet_decode(*alpha, code);
lua_pushlstring(L, &character, 1);
return 1;
}
static int hcr_huffman_write_base_qual_freq(GtUword symbol,
GtUint64 freq,
GT_UNUSED GtBitsequence code,
GT_UNUSED unsigned code_length,
void *pt)
{
GtUchar base,
qual;
WriteNodeInfo *info = (WriteNodeInfo*)pt;
gt_safe_assign(base, (symbol % gt_alphabet_size(info->alpha)));
if (base == (GtUchar) gt_alphabet_size(info->alpha) - 1)
base = (GtUchar) WILDCARD;
gt_safe_assign(base, (toupper(gt_alphabet_decode(info->alpha, base))));
gt_xfwrite_one(&base, info->output);
gt_safe_assign(qual,
(symbol / gt_alphabet_size(info->alpha) + info->qual_offset));
gt_xfwrite_one(&qual, info->output);
gt_xfwrite_one(&freq, info->output);
return 0;
}
static int hcr_next_seq_qual(GtHcrSeqDecoder *seq_dec, char *seq, char *qual,
GtError *err)
{
enum state {
HCR_ERROR = -1,
END,
SUCCESS
};
unsigned char base;
GtUword i,
nearestsample,
*symbol;
size_t startofnearestsample = 0;
enum state status = END;
FastqFileInfo cur_read;
FastqFileInfo *fileinfo = NULL;
if (seq_dec->cur_read <= seq_dec->num_of_reads) {
status = SUCCESS;
if (seq_dec->symbols == NULL)
seq_dec->symbols = gt_array_new(sizeof (GtUword));
else
gt_array_reset(seq_dec->symbols);
cur_read.readnum = seq_dec->cur_read;
gt_log_log("cur_read: "GT_WU"",seq_dec->cur_read);
fileinfo = (FastqFileInfo *)gt_rbtree_next_key(seq_dec->file_info_rbt,
&cur_read,
hcr_cmp_FastqFileInfo,
NULL);
gt_assert(fileinfo);
/* reset huffman_decoder if next read is sampled */
if (gt_sampling_get_next_elementnum(seq_dec->sampling) ==
seq_dec->cur_read) {
gt_log_log("reset because sampled read is next");
(void) gt_sampling_get_next_sample(seq_dec->sampling,
&nearestsample,
&startofnearestsample);
reset_data_iterator_to_pos(seq_dec->data_iter, startofnearestsample);
(void) gt_huffman_decoder_get_new_mem_chunk(seq_dec->huff_dec, err);
if (gt_error_is_set(err))
status = HCR_ERROR;
}
if (status != HCR_ERROR) {
int ret;
ret = gt_huffman_decoder_next(seq_dec->huff_dec, seq_dec->symbols,
fileinfo->readlength, err);
if (ret != 1)
status = HCR_ERROR;
if (ret == 0)
gt_error_set(err, "reached end of file");
}
if (qual || seq) {
gt_log_log("set strings");
for (i = 0; i < gt_array_size(seq_dec->symbols); i++) {
symbol = (GtUword*) gt_array_get(seq_dec->symbols, i);
if (qual != NULL)
qual[i] = get_qual_from_symbol(seq_dec, *symbol);
if (seq != NULL) {
base = get_base_from_symbol(seq_dec, *symbol);
seq[i] = (char)toupper(gt_alphabet_decode(seq_dec->alpha,
(GtUchar) base));
}
}
if (qual != NULL)
qual[gt_array_size(seq_dec->symbols)] = '\0';
if (seq != NULL)
seq[gt_array_size(seq_dec->symbols)] = '\0';
}
seq_dec->cur_read++;
}
return (int) status;
}