def _get_header_from_lines(self, lines):
header = libcbcf.VariantHeader()
for line in lines[:-1]:
header.add_line(line)
return vcf_header_io.VcfHeader(infos=header.info,
filters=header.filters,
alts=header.alts,
formats=header.formats,
contigs=header.contigs)
def get_vcf_headers(input_file):
if not FileSystems.exists(input_file):
raise ValueError('VCF header does not exist')
header = libcbcf.VariantHeader()
lines = _header_line_generator(input_file)
sample_line = None
header.add_line('##fileformat=VCFv4.0\n')
file_empty = True
read_file_format_line = False
for line in lines:
if not read_file_format_line:
read_file_format_line = True
if line and not line.startswith(
vcf_header_io.FILE_FORMAT_HEADER_TEMPLATE.format(
VERSION='')):
header.add_line(
vcf_header_io.FILE_FORMAT_HEADER_TEMPLATE.format(
VERSION='4.0'))
if line.startswith('##'):
header.add_line(line.strip())
file_empty = False
elif line.startswith('#'):
sample_line = line.strip()
file_empty = False
elif line:
# If non-empty non-header line exists, #CHROM line has to be supplied.
if not sample_line:
raise ValueError('Header line is missing')
else:
if file_empty:
raise ValueError('File is empty')
# If no records were found, use dummy #CHROM line for sample extraction.
if not sample_line:
sample_line = vcf_header_io.LAST_HEADER_LINE_PREFIX
return vcf_header_io.VcfHeader(infos=header.info,
filters=header.filters,
alts=header.alts,
formats=header.formats,
contigs=header.contigs,
samples=sample_line,
file_path=input_file)
def _get_vcf_header_from_lines(lines, file_name=None):
header = libcbcf.VariantHeader()
sample_line = LAST_HEADER_LINE_PREFIX
header.add_line('##fileformat=VCFv4.0')
for line in lines:
if line.startswith('#'):
if line.startswith(LAST_HEADER_LINE_PREFIX):
sample_line = line.strip()
break
header.add_line(line.strip())
else:
break
return VcfHeader(infos=header.info,
filters=header.filters,
alts=header.alts,
formats=header.formats,
contigs=header.contigs,
samples=sample_line,
file_path=file_name)
def read_records(
self,
file_path, # type: str
unused_range_tracker, # type: range_trackers.UnsplittableRangeTracker
):
# type: (...) -> Iterable[VcfHeader]
header = libcbcf.VariantHeader()
lines = self._read_headers_plus_one_record(file_path)
sample_line = None
read_file_format_line = False
for line in lines:
if not read_file_format_line:
read_file_format_line = True
if line and not line.startswith(
FILE_FORMAT_HEADER_TEMPLATE.format(VERSION='')):
header.add_line(
FILE_FORMAT_HEADER_TEMPLATE.format(VERSION='4.0'))
if line.startswith('##'):
header.add_line(line.strip())
elif line.startswith('#'):
sample_line = line
elif line:
# If non-empty non-header line exists, #CHROM line has to be supplied.
if not sample_line:
raise ValueError('Header line is missing')
else:
# If no records were found, use dummy #CHROM line for sample extraction.
if not sample_line:
sample_line = LAST_HEADER_LINE_PREFIX
yield VcfHeader(infos=header.info,
filters=header.filters,
alts=header.alts,
formats=header.formats,
contigs=header.contigs,
samples=sample_line,
file_path=file_path)
