def _create_dict(obj_func, columns, getters, validator, dictgetters):
obj = apply(obj_func)
pre_dict = obj_to_dict(obj, dictzip(columns, getters))
#optional intermediate schema here
if dictgetters:
extra_dict = obj_to_dict(pre_dict, dictgetters)
full_dict = merge_dicts(pre_dict, extra_dict)
else:
full_dict = pre_dict
return validator.validate(full_dict)
def _create_dict(obj_func, columns, getters, validator, dictgetters):
obj = apply(obj_func)
pre_dict = obj_to_dict(obj, dictzip(columns, getters))
#optional intermediate schema here
if dictgetters:
extra_dict = obj_to_dict(pre_dict, dictgetters)
full_dict = merge_dicts(pre_dict, extra_dict)
else:
full_dict = pre_dict
return validator.validate(full_dict)
def parse_cigar(cigar_str):
#? makes the regex not be too greedy
cigar_regex = r'(?:([0-9]+)([MIDNSHPX=]))+?'
reg = re.compile(cigar_regex)
tups = reg.findall(cigar_str)
key, value = itemgetter(1), itemgetter(0)
groups = groupby(sorted(tups, key=key), key)
get_counts = pmap(compose(int, itemgetter(0)))
sum_counts = compose(sum, get_counts)
s = "cigar_{0}".format
cigar_dict = dict( (s(name), sum_counts(nums)) for name, nums in groups)
#print cigar_dict
mismatches = sum(num for k, num in cigar_dict.items() if k not in ['cigar_M', 'cigar_='])
return merge_dicts(cigar_dict, {'cigar_score': mismatches})
def get_row(row):
result = all_but_cigar_dict(row)
return merge_dicts(result, get_cigar_dict(result), get_flag_dict(result), {'error' : get_error(result)})
