def aggregate_file(filename, filetype, assembly, chromsizes_filename,
has_header):
if filetype == 'bedfile':
if assembly is None and chromsizes_filename is None:
print(
'An assembly or set of chromosome sizes is required when importing bed files. Please specify one or the other using the --assembly or --chromsizes-filename parameters',
file=sys.stderr)
return
with tempfile.TemporaryDirectory() as td:
output_file = op.join(td, filename + '.beddb')
print("Aggregating bedfile")
cca._bedfile(filename,
output_file,
assembly,
importance_column='random',
has_header=has_header,
chromosome=None,
max_per_tile=50,
delimiter=None,
chromsizes_filename=chromsizes_filename,
offset=0,
tile_size=1024)
to_import = output_file
# because we aggregated the file, the new filetype is beddb
filetype = 'beddb'
return (to_import, filetype)
elif filetype == 'bedpe':
if assembly is None and chromsizes_filename is None:
print(
'An assembly or set of chromosome sizes is required when importing bed files. Please specify one or the other using the --assembly or --chromsizes-filename parameters',
file=sys.stderr)
return
with tempfile.TemporaryDirectory() as td:
output_file = op.join(td, filename + '.beddb')
print("Aggregating bedfile")
cca._bedpe(filename,
output_file,
assembly,
importance_column='random',
has_header=has_header,
chromosome=None,
max_per_tile=50,
chromsizes_filename=chromsizes_filename,
tile_size=1024)
to_import = output_file
# because we aggregated the file, the new filetype is beddb
filetype = 'bed2ddb'
return (to_import, filetype)
else:
return (filename, filetype)
def test_nonstandard_chrom():
filename = 'test/sample_data/test_non_standard_chrom.bed'
f = tempfile.NamedTemporaryFile(delete=False)
ret = cca._bedfile(filename, f.name,
'hg19', None, False,
None, 100, 1024, None, None, 0)
assert ret is None
ret = cca._bedfile(filename, f.name,
'dfsdfs', None, False,
None, 100, 1024, None, None, 0)
assert ret is None
def aggregate_file(filename, filetype, assembly, chromsizes_filename,
has_header, no_upload, tmp_dir):
if filetype == 'bedfile':
if no_upload:
raise Exception(
"Bedfile files need to be aggregated and cannot be linked. Consider not using the --link-file option",
file=sys.stderr)
if assembly is None and chromsizes_filename is None:
print(
'An assembly or set of chromosome sizes is required when importing bed files. Please specify one or the other using the --assembly or --chromsizes-filename parameters',
file=sys.stderr)
return
output_file = op.join(tmp_dir, filename + '.beddb')
print("Aggregating bedfile")
cca._bedfile(filename,
output_file,
assembly,
importance_column='random',
has_header=has_header,
chromosome=None,
max_per_tile=50,
delimiter=None,
chromsizes_filename=chromsizes_filename,
offset=0,
tile_size=1024)
to_import = output_file
# because we aggregated the file, the new filetype is beddb
filetype = 'beddb'
return (to_import, filetype)
elif filetype == 'bedpe':
if no_upload:
raise Exception(
"Bedpe files need to be aggregated and cannot be linked. Consider not using the --link-file option",
file=sys.stderr)
if assembly is None and chromsizes_filename is None:
print(
'An assembly or set of chromosome sizes is required when importing bed files. Please specify one or the other using the --assembly or --chromsizes-filename parameters',
file=sys.stderr)
return
output_file = op.join(tmp_dir, filename + '.bed2ddb')
print("Aggregating bedpe")
cca._bedpe(filename,
output_file,
assembly,
importance_column='random',
has_header=has_header,
chromosome=None,
max_per_tile=50,
chromsizes_filename=chromsizes_filename,
tile_size=1024)
to_import = output_file
# because we aggregated the file, the new filetype is beddb
filetype = 'bed2ddb'
return (to_import, filetype)
else:
return (filename, filetype)