def setUp(self):
self.unindexed_options = variants_pb2.VcfReaderOptions()
self.indexed_options = variants_pb2.VcfReaderOptions(
index_mode=index_pb2.INDEX_BASED_ON_FILENAME)
self.sites_vcf = test_utils.genomics_core_testdata('test_sites.vcf')
self.samples_vcf = test_utils.genomics_core_testdata('test_samples.vcf.gz')
self.sites_reader = vcf_reader.VcfReader.from_file(self.sites_vcf,
self.unindexed_options)
self.samples_reader = vcf_reader.VcfReader.from_file(
self.samples_vcf, self.indexed_options)
def __init__(self,
input_path,
use_index=True,
excluded_info_fields=None,
excluded_format_fields=None):
"""Initializer for NativeVcfReader.
Args:
input_path: str. The path to the VCF file to read.
use_index: bool. If True, the input is assumed to be bgzipped and tabix
indexed, and the `query` functionality is supported.
excluded_info_fields: list(str). A list of INFO field IDs that should not
be parsed into the Variants. If None, all INFO fields are included.
excluded_format_fields: list(str). A list of FORMAT field IDs that should
not be parsed into the Variants. If None, all FORMAT fields are
included.
"""
super(NativeVcfReader, self).__init__()
index_mode = index_pb2.INDEX_BASED_ON_FILENAME
if not use_index:
index_mode = index_pb2.DONT_USE_INDEX
self._reader = vcf_reader.VcfReader.from_file(
input_path.encode('utf8'),
variants_pb2.VcfReaderOptions(
index_mode=index_mode,
excluded_info_fields=excluded_info_fields,
excluded_format_fields=excluded_format_fields))
self.header = self._reader.header
self.field_access_cache = VcfHeaderCache(self.header)
def __init__(self,
input_path,
excluded_info_fields=None,
excluded_format_fields=None,
store_gl_and_pl_in_info_map=False):
"""Initializer for NativeVcfReader.
Args:
input_path: str. The path to the VCF file to read.
excluded_info_fields: list(str). A list of INFO field IDs that should not
be parsed into the Variants. If None, all INFO fields are included.
excluded_format_fields: list(str). A list of FORMAT field IDs that should
not be parsed into the Variants. If None, all FORMAT fields are
included.
store_gl_and_pl_in_info_map: bool. If True, the "GL" and "PL" FORMAT
fields are stored in the VariantCall.info map rather than as top-level
values in the VariantCall.genotype_likelihood field.
"""
super(NativeVcfReader, self).__init__()
self._reader = vcf_reader.VcfReader.from_file(
input_path.encode('utf8'),
variants_pb2.VcfReaderOptions(
excluded_info_fields=excluded_info_fields,
excluded_format_fields=excluded_format_fields,
store_gl_and_pl_in_info_map=store_gl_and_pl_in_info_map,
))
self.header = self._reader.header
self.field_access_cache = VcfHeaderCache(self.header)
def setUp(self):
self.sites_vcf = test_utils.genomics_core_testdata('test_sites.vcf')
self.samples_vcf = test_utils.genomics_core_testdata('test_samples.vcf.gz')
self.options = variants_pb2.VcfReaderOptions()
self.sites_reader = vcf_reader.VcfReader.from_file(self.sites_vcf,
self.options)
self.samples_reader = vcf_reader.VcfReader.from_file(
self.samples_vcf, self.options)
def _init_with_header(self, header_lines):
# The first header line must be similar to '##fileformat=VCFv.*'.
if header_lines and not header_lines[0].startswith(
FILE_FORMAT_HEADER_TEMPLATE.format(VERSION='')):
header_lines.insert(0, FILE_FORMAT_HEADER_TEMPLATE.format(VERSION='4.0'))
try:
self._vcf_reader = nucleus_vcf_reader.VcfReader.from_file(
self._store_to_temp_local_file(header_lines),
variants_pb2.VcfReaderOptions()) # pylint: disable=c-extension-no-member
except ValueError as e:
raise ValueError(
'Invalid VCF header in %s: %s' % (self._file_name, str(e)))
self._extract_header_fields()
