def test_roundtrip_writer(self, filename):
output_path = test_utils.test_tmpfile(filename)
with bed.BedWriter(output_path,
header=bed_pb2.BedHeader(num_fields=5)) as writer:
for record in self.records:
writer.write(record)
with bed.BedReader(output_path) as reader:
v2_records = list(reader.iterate())
self.assertEqual(self.records, v2_records)
def setUp(self):
out_fname = test_utils.test_tmpfile('output.bed')
self.writer = bed_writer.BedWriter.to_file(
out_fname, bed_pb2.BedHeader(num_fields=12), bed_pb2.BedWriterOptions())
self.expected_bed_content = [
'chr1\t10\t20\tfirst\t100\t+\t12\t18\t255,124,1\t3\t2,6,2\t10,12,18\n',
'chr1\t100\t200\tsecond\t250\t.\t120\t180\t252,122,12\t2\t35,40\t'
'100,160\n'
]
self.record = bed_pb2.BedRecord(
reference_name='chr1', start=20, end=30, name='r')
def __init__(self, output_path, header=None):
"""Initializer for NativeBedWriter.
Args:
output_path: str. The path to which to write the BED file.
header: nucleus.genomics.v1.BedHeader. The header that defines all
information germane to the constituent BED records.
"""
super(NativeBedWriter, self).__init__()
if header is None:
header = bed_pb2.BedHeader(num_fields=3)
writer_options = bed_pb2.BedWriterOptions()
self._writer = bed_writer.BedWriter.to_file(output_path, header,
writer_options)
def test_writing_canned_records(self):
"""Tests writing all the records that are 'canned' in our tfrecord file."""
# This file is in TFRecord format.
tfrecord_file = test_utils.genomics_core_testdata(
'test_regions.bed.tfrecord')
header = bed_pb2.BedHeader(num_fields=12)
writer_options = bed_pb2.BedWriterOptions()
bed_records = list(
io_utils.read_tfrecords(tfrecord_file, proto=bed_pb2.BedRecord))
out_fname = test_utils.test_tmpfile('output.bed')
with bed_writer.BedWriter.to_file(out_fname, header,
writer_options) as writer:
for record in bed_records:
writer.write(record)
with gfile.GFile(out_fname, 'r') as f:
self.assertEqual(f.readlines(), self.expected_bed_content)