def main(args):
"""
@param args: positional and flaglike arguments
"""
# read the arguments
input_filename = os.path.abspath(os.path.expanduser(args.infile))
output_directory = os.path.abspath(os.path.expanduser(args.outdir))
force = args.force
# make sure that the output directory exists
if not os.path.isdir(output_directory):
if force:
os.makedirs(output_directory)
if not os.path.isdir(output_directory):
msg = 'output directory does not exist: ' + output_directory
raise Exception(msg)
# scan the input file for chromosome names
ch_paths = []
skimmer = DGRP.ChromoSkimmer()
with open(input_filename) as fin:
for chromo_name in skimmer.skim(gen_untyped_rows(fin)):
output_filename = args.out_prefix + chromo_name + args.out_suffix
ch_path = os.path.join(output_directory, output_filename)
ch_paths.append(ch_path)
if not force:
if os.path.exists(ch_path):
raise Exception('output already exists: ' + ch_path)
chromo_names = skimmer.name_list
nlines = skimmer.linecount
# start the progress bar
nticks = 2 * nlines
pbar = Progress.Bar(nticks)
# scan the input file for correct types and for monotonicity
with open(input_filename) as fin:
for i in DGRP.check_chromo_monotonicity(gen_typed_rows(fin)):
pbar.increment()
# create the files open for writing
ch_files = []
for p in ch_paths:
ch_files.append(open(p, 'wt'))
# write the headers
if not args.noheader:
for f in ch_files:
f.write(g_header + '\n')
# write the lines
name_to_file = dict(zip(chromo_names, ch_files))
with open(input_filename) as fin:
for row in gen_typed_rows(fin):
name = row[0]
row_out = convert_row(row)
f = name_to_file[name]
line_out = '\t'.join(str(x) for x in row_out)
f.write(line_out + '\n')
pbar.increment()
# close the files
for f in ch_files:
f.close()
def get_response_content(fs):
# quickly skim the lines to get some info
fin = StringIO(fs.data_in)
skimmer = DGRP.ChromoSkimmer()
for chromo_name in skimmer.skim(gen_untyped_rows(fin)):
pass
chromo_names = skimmer.name_list
nlines = skimmer.linecount
# check formatting and monotonicity
fin = StringIO(fs.data_in)
for i in DGRP.check_chromo_monotonicity(gen_typed_rows(fin)):
pass
# begin writing
out = StringIO()
print >> out, 'writing the first of', len(chromo_names), 'chromosomes:'
print >> out
# write only the first chromosome
fin = StringIO(fs.data_in)
print >> out, g_header
for row in gen_typed_rows(fin):
name = row[0]
if name == chromo_names[0]:
print >> out, '\t'.join(str(x) for x in convert_row(row))
return out.getvalue()
