static int parse_score_line(GtScoreMatrix *sm, GtTokenizer *tz,
GtArray *index_to_alpha_char_mapping,
char *parsed_characters, GtError *err)
{
unsigned int num_of_chars, i = 0;
char amino_acid;
int score, had_err = 0;
GtStr *token;
gt_assert(sm && tz && index_to_alpha_char_mapping);
gt_error_check(err);
token = gt_tokenizer_get_token(tz);
gt_assert(token);
if (gt_str_length(token) != 1) {
gt_error_set(err, "illegal character token '%s' on line %lu in file '%s'",
gt_str_get(token), gt_tokenizer_get_line_number(tz),
gt_tokenizer_get_filename(tz));
had_err = -1;
}
amino_acid = gt_str_get(token)[0];
/* check for character duplications */
if (parsed_characters[(int) amino_acid]) {
gt_error_set(err, "multiple character '%c' entry on line %lu in file '%s'",
amino_acid, gt_tokenizer_get_line_number(tz),
gt_tokenizer_get_filename(tz));
had_err = -1;
}
parsed_characters[(int) amino_acid] = GT_UNDEF_CHAR;
gt_str_delete(token);
if (!had_err) {
num_of_chars = gt_alphabet_num_of_chars(sm->alphabet);
gt_tokenizer_next_token(tz);
while ((token = gt_tokenizer_get_token(tz))) {
unsigned int idx1, idx2;
/* the tokenizer can return tokens which are empty except for a newline
-> skip these */
if (!strcmp(gt_str_get(token), "\n")) {
gt_str_delete(token);
gt_tokenizer_next_token(tz);
if (gt_tokenizer_line_start(tz))
break;
continue;
}
/* token is not empty -> parse score */
had_err = gt_parse_int_line(&score, gt_str_get(token),
gt_tokenizer_get_line_number(tz),
gt_tokenizer_get_filename(tz), err);
if (had_err)
break;
idx1 = gt_alphabet_encode(sm->alphabet, amino_acid);
idx2 = gt_alphabet_encode(sm->alphabet, *(char*)
gt_array_get(index_to_alpha_char_mapping, i));
gt_score_matrix_set_score(sm,
idx1 == WILDCARD ? num_of_chars : idx1,
idx2 == WILDCARD ? num_of_chars : idx2,
score);
i++;
gt_str_delete(token);
gt_tokenizer_next_token(tz);
if (gt_tokenizer_line_start(tz))
break;
}
}
return had_err;
}
static int parse_alphabet_line(GtArray *index_to_alpha_char_mapping,
GtTokenizer *tz, GtError *err)
{
GtStr *token;
char *tokenstr, amino_acid, parsed_characters[UCHAR_MAX] = { 0 };
int had_err = 0;
gt_error_check(err);
gt_assert(index_to_alpha_char_mapping && tz);
gt_assert(!gt_array_size(index_to_alpha_char_mapping));
while ((token = gt_tokenizer_get_token(tz))) {
if (gt_str_length(token) > 2) {
gt_error_set(err, "illegal character token '%s' on line %lu in file '%s'",
gt_str_get(token), gt_tokenizer_get_line_number(tz),
gt_tokenizer_get_filename(tz));
had_err = -1;
break;
}
tokenstr = gt_str_get(token);
amino_acid = tokenstr[0];
/* check for character duplications */
if (parsed_characters[(int) amino_acid]) {
gt_error_set(err, "the character '%c' appears more then once on line %lu "
"in file '%s'", amino_acid,
gt_tokenizer_get_line_number(tz),
gt_tokenizer_get_filename(tz));
had_err = -1;
break;
}
parsed_characters[(int) amino_acid] = GT_UNDEF_CHAR;
if (amino_acid == '\n') {
gt_str_delete(token);
gt_tokenizer_next_token(tz);
gt_assert(!had_err);
return 0;
}
gt_array_add(index_to_alpha_char_mapping, amino_acid);
if (gt_str_length(token) == 2) {
if (tokenstr[1] != '\n') {
gt_error_set(err, "illegal character token '%s' on line %lu in file "
"'%s'", gt_str_get(token),
gt_tokenizer_get_line_number(tz),
gt_tokenizer_get_filename(tz));
had_err = -1;
break;
}
gt_str_delete(token);
gt_tokenizer_next_token(tz);
gt_assert(!had_err);
return 0;
}
gt_str_delete(token);
gt_tokenizer_next_token(tz);
}
if (!had_err) {
if (!gt_array_size(index_to_alpha_char_mapping)) {
gt_error_set(err, "could not parse a single alphabet character in file "
"'%s' (file empty or directory?)",
gt_tokenizer_get_filename(tz));
had_err = -1;
}
}
gt_str_delete(token);
return had_err;
}
static int gt_gdiffcalc_runner(int argc, const char **argv, int parsed_args,
void *tool_arguments, GT_UNUSED GtError *err)
{
GtGenomediffArguments *arguments = tool_arguments;
int had_err = 0, i;
GtUword lcounter = 0, zcounter = 0;
double **shusums = NULL;
GtEncseq *encseq = NULL;
GtLogger *logger;
GtShuUnitFileInfo *unit_info = NULL;
GtTimer *timer = NULL;
gt_error_check(err);
gt_assert(arguments);
logger = gt_logger_new(arguments->verbose,
GT_LOGGER_DEFLT_PREFIX,
stdout);
gt_assert(logger);
for (i = parsed_args; i < argc; i++) {
gt_str_array_add_cstr(arguments->filenames, argv[i]);
}
if (gt_showtime_enabled()) {
timer = gt_timer_new_with_progress_description("load encseq");
gt_timer_start(timer);
gt_assert(timer);
}
if (arguments->with_units) {
gt_logger_log(logger, "unitfile option set, filename is %s\n",
gt_str_get(arguments->unitfile));
}
if (!had_err) {
GtEncseqLoader *el = gt_encseq_loader_new_from_options(arguments->loadopts,
err);
encseq =
gt_encseq_loader_load(el, gt_str_get(arguments->indexname), err);
gt_encseq_loader_delete(el);
}
if (encseq == NULL)
had_err = -1;
if (timer != NULL)
gt_timer_show_progress(timer, "load units", stdout);
if (!had_err) {
unit_info = gt_shu_unit_info_new(encseq);
if (arguments->with_units)
had_err = gt_shu_unit_file_info_read(arguments->unitfile, unit_info,
logger, err);
}
if (timer != NULL)
gt_timer_show_progress(timer, "read table", stdout);
if (!had_err) {
GtIO *table_file = NULL;
GtTokenizer *tokenizer = NULL;
GtStr *line = NULL;
gt_assert(unit_info != NULL);
gt_array2dim_calloc(shusums, unit_info->num_of_genomes,
unit_info->num_of_genomes);
table_file = gt_io_new(gt_str_array_get(arguments->filenames, 0), "r");
tokenizer = gt_tokenizer_new(table_file);
line = gt_tokenizer_get_token(tokenizer);
while (line != NULL && !had_err) {
char *cline = gt_str_get(line);
char *elem = strtok(cline, ";");
zcounter = 0;
while (elem != NULL && !had_err) {
if (*elem != '#') {
if (1 != sscanf(elem, "%lf",
&shusums[lcounter][zcounter])) {
had_err = 1;
gt_error_set(err, "couldn't scan");
break;
}
gt_logger_log(logger,"wert: %lf", shusums[lcounter][zcounter]);
zcounter++;
}
else {
gt_logger_log(logger, "name: %s", elem++);
}
elem = strtok(NULL, ";");
}
gt_tokenizer_next_token(tokenizer);
gt_str_delete(line);
line = gt_tokenizer_get_token(tokenizer);
lcounter++;
gt_logger_log(logger, "line "GT_WD"", lcounter);
}
}
if (!had_err) {
GtUword num_of_seq, file_idx, seq_idx, startpos;
GT_UNUSED GtUword oldpos = 0;
gt_assert(unit_info != NULL);
gt_assert(lcounter == zcounter);
gt_assert(lcounter == unit_info->num_of_genomes);
num_of_seq = gt_encseq_num_of_sequences(unit_info->encseq);
for (seq_idx = 0; seq_idx < num_of_seq; seq_idx++) {
startpos = gt_encseq_seqstartpos(unit_info->encseq, seq_idx);
file_idx = gt_encseq_filenum(unit_info->encseq, startpos);
gt_log_log("seq: "GT_WU" starts at: "GT_WU"\n"
"belonges to file: "GT_WU" which is part of genome: %s",
seq_idx, startpos, file_idx,
gt_str_array_get(unit_info->genome_names,
unit_info->map_files[file_idx]));
gt_assert(oldpos <= startpos);
oldpos = startpos;
}
}
if (!had_err && shusums != NULL) {
had_err = gt_genomediff_calculate_div_from_avg(shusums, arguments,
unit_info,
logger, timer, err);
gt_array2dim_delete(shusums);
}
if (timer != NULL) {
gt_timer_show_progress_final(timer, stdout);
gt_timer_delete(timer);
}
gt_logger_delete(logger);
gt_encseq_delete(encseq);
gt_shu_unit_info_delete(unit_info);
return had_err;
}
