def _fasta_sniffer(fh):
# Strategy:
# Ignore up to 5 blank/whitespace-only lines at the beginning of the
# file. Read up to 10 records. If at least one record is read (i.e.
# the file isn't empty) and no errors are thrown during reading, assume
# the file is in FASTA format. If a record appears to be QUAL, do *not*
# identify the file as FASTA since we don't want to sniff QUAL files as
# FASTA (technically they can be read as FASTA since the sequences may
# not be validated but it probably isn't what the user wanted). Also, if
# we add QUAL as its own file format in the future, we wouldn't want the
# FASTA and QUAL sniffers to both positively identify a QUAL file.
if _too_many_blanks(fh, 5):
return False, {}
num_records = 10
empty = True
try:
parser = _parse_fasta_raw(fh, _sniffer_data_parser, FASTAFormatError)
for _ in zip(range(num_records), parser):
empty = False
except FASTAFormatError:
return False, {}
if empty:
return False, {}
else:
return True, {}
def _fasta_sniffer(fh):
# Strategy:
# Ignore up to 5 blank/whitespace-only lines at the beginning of the
# file. Read up to 10 records. If at least one record is read (i.e.
# the file isn't empty) and no errors are thrown during reading, assume
# the file is in FASTA format. If a record appears to be QUAL, do *not*
# identify the file as FASTA since we don't want to sniff QUAL files as
# FASTA (technically they can be read as FASTA since the sequences may
# not be validated but it probably isn't what the user wanted). Also, if
# we add QUAL as its own file format in the future, we wouldn't want the
# FASTA and QUAL sniffers to both positively identify a QUAL file.
if _too_many_blanks(fh, 5):
return False, {}
num_records = 10
empty = True
try:
parser = _parse_fasta_raw(fh, _sniffer_data_parser, FASTAFormatError)
for _ in zip(range(num_records), parser):
empty = False
except FASTAFormatError:
return False, {}
if empty:
return False, {}
else:
return True, {}
def _embl_sniffer(fh):
# check the 1st real line is a valid ID line
if _too_many_blanks(fh, 5):
return False, {}
try:
line = next(_line_generator(fh, skip_blanks=True, strip=False))
except StopIteration:
return False, {}
if line.startswith('ID'):
return True, {}
else:
return False, {}
def _embl_sniffer(fh):
# check the 1st real line is a valid ID line
if _too_many_blanks(fh, 5):
return False, {}
try:
line = next(_line_generator(fh, skip_blanks=True, strip=False))
except StopIteration:
return False, {}
if line.startswith('ID'):
return True, {}
else:
return False, {}
def _genbank_sniffer(fh):
# check the 1st real line is a valid LOCUS line
if _too_many_blanks(fh, 5):
return False, {}
try:
line = next(_line_generator(fh, skip_blanks=True, strip=False))
except StopIteration:
return False, {}
try:
_parse_locus([line])
except GenBankFormatError:
return False, {}
return True, {}
def _genbank_sniffer(fh):
# check the 1st real line is a valid LOCUS line
if _too_many_blanks(fh, 5):
return False, {}
try:
line = next(_line_generator(fh, skip_blanks=True, strip=False))
except StopIteration:
return False, {}
try:
_parse_locus([line])
except GenBankFormatError:
return False, {}
return True, {}
def _gff3_sniffer(fh):
# check the 1st real line is a valid ID line
if _too_many_blanks(fh, 5):
return False, {}
try:
line = next(_line_generator(fh, skip_blanks=True, strip=False))
except StopIteration:
return False, {}
if re.match(r'##gff-version\s+3', line):
return True, {}
else:
return False, {}
def _gff3_sniffer(fh):
# check the 1st real line is a valid ID line
if _too_many_blanks(fh, 5):
return False, {}
try:
line = next(_line_generator(fh, skip_blanks=True, strip=False))
except StopIteration:
return False, {}
if re.match(r'##gff-version\s+3', line):
return True, {}
else:
return False, {}
def _fastq_sniffer(fh):
# Strategy:
# Ignore up to 5 blank/whitespace-only lines at the beginning of the
# file. Read up to 10 records. If at least one record is read (i.e. the
# file isn't empty) and the quality scores are in printable ASCII range,
# assume the file is FASTQ.
if _too_many_blanks(fh, 5):
return False, {}
try:
not_empty = False
for _ in zip(range(10), _fastq_to_generator(fh, phred_offset=33)):
not_empty = True
return not_empty, {}
except (FASTQFormatError, ValueError):
return False, {}
def _fastq_sniffer(fh):
# Strategy:
# Ignore up to 5 blank/whitespace-only lines at the beginning of the
# file. Read up to 10 records. If at least one record is read (i.e. the
# file isn't empty) and the quality scores are in printable ASCII range,
# assume the file is FASTQ.
if _too_many_blanks(fh, 5):
return False, {}
try:
not_empty = False
for _ in zip(range(10), _fastq_to_generator(fh, phred_offset=33)):
not_empty = True
return not_empty, {}
except (FASTQFormatError, ValueError):
return False, {}
def _fastq_sniffer(fh):
# Strategy:
# Ignore up to 5 blank/whitespace-only lines at the beginning of the
# file. Read up to 10 records. If at least one record is read (i.e. the
# file isn't empty) and the quality scores are in printable ASCII range,
# assume the file is FASTQ.
if _too_many_blanks(fh, 5):
return False, {}
try:
not_empty = False
for _, seq in zip(range(10), _fastq_to_generator(fh, phred_offset=33)):
split_length = len((seq.metadata['id'] +
seq.metadata['description']).split(':'))
description = seq.metadata['description'].split(':')
if split_length == 10 and description[1] in 'YN':
return True, {'variant': 'illumina1.8'}
not_empty = True
return not_empty, {}
except (FASTQFormatError, ValueError):
return False, {}