Ejemplo n.º 1
0
/* the score matrix parser */
static int parse_score_matrix(GtScoreMatrix *sm, const char *path,
                              GtError *err)
{
  GtTokenizer *tz;
  GtArray *index_to_alpha_char_mapping;
  unsigned int parsed_score_lines = 0;
  char parsed_characters[UCHAR_MAX] = { 0 };
  int had_err = 0;
  gt_error_check(err);
  gt_assert(sm && path && sm->alphabet);
  tz = gt_tokenizer_new(gt_io_new(path, "r"));
  index_to_alpha_char_mapping = gt_array_new(sizeof (char));
  gt_tokenizer_skip_comment_lines(tz);
  had_err = parse_alphabet_line(index_to_alpha_char_mapping, tz, err);
  if (!had_err) {
    while (gt_tokenizer_has_token(tz)) {
      had_err = parse_score_line(sm, tz, index_to_alpha_char_mapping,
                                 parsed_characters, err);
      if (had_err)
        break;
      parsed_score_lines++;
    }
  }

  /* check the number of parsed score lines */
  if (!had_err &&
      parsed_score_lines != gt_array_size(index_to_alpha_char_mapping)) {
    gt_error_set(err, "the score matrix given in '%s' is not symmetric", path);
    had_err = -1;
  }

  gt_array_delete(index_to_alpha_char_mapping);
  gt_tokenizer_delete(tz);

  return had_err;
}
Ejemplo n.º 2
0
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;
}