def _format_fasta_like_records(generator, id_whitespace_replacement,
description_newline_replacement, require_qual,
lowercase=None):
if ((id_whitespace_replacement is not None and
'\n' in id_whitespace_replacement) or
(description_newline_replacement is not None and
'\n' in description_newline_replacement)):
raise ValueError(
"Newline character (\\n) cannot be used to replace whitespace in "
"sequence IDs, nor to replace newlines in sequence descriptions.")
for idx, seq in enumerate(generator):
if len(seq) < 1:
raise ValueError(
"%s sequence does not contain any characters (i.e., it is an "
"empty/blank sequence). Writing empty sequences is not "
"supported." % cardinal_to_ordinal(idx + 1))
if 'id' in seq.metadata:
id_ = seq.metadata['id']
else:
id_ = ''
if id_whitespace_replacement is not None:
id_ = _whitespace_regex.sub(id_whitespace_replacement, id_)
if 'description' in seq.metadata:
desc = seq.metadata['description']
else:
desc = ''
if description_newline_replacement is not None:
desc = _newline_regex.sub(description_newline_replacement, desc)
if desc:
header = '%s %s' % (id_, desc)
else:
header = id_
if require_qual and 'quality' not in seq.positional_metadata:
raise ValueError(
"Cannot write %s sequence because it does not have quality "
"scores associated with it." % cardinal_to_ordinal(idx + 1))
qual = None
if 'quality' in seq.positional_metadata:
qual = seq.positional_metadata['quality'].values
if lowercase is not None:
if hasattr(seq, 'lowercase'):
seq_str = seq.lowercase(lowercase)
else:
raise AttributeError("lowercase specified but class %s does "
"not support lowercase functionality" %
seq.__class__.__name__)
else:
seq_str = str(seq)
yield header, seq_str, qual
def test_valid_range(self):
# taken and modified from http://stackoverflow.com/a/20007730/3776794
exp = ['0th', '1st', '2nd', '3rd', '4th', '5th', '6th', '7th', '8th',
'9th', '10th', '11th', '12th', '13th', '14th', '15th', '16th',
'17th', '18th', '19th', '20th', '21st', '22nd', '23rd', '24th',
'25th', '26th', '27th', '28th', '29th', '30th', '31st', '32nd',
'100th', '101st', '42042nd']
obs = [cardinal_to_ordinal(n) for n in
list(range(0, 33)) + [100, 101, 42042]]
self.assertEqual(obs, exp)
def test_valid_range(self):
# taken and modified from http://stackoverflow.com/a/20007730/3776794
exp = ['0th', '1st', '2nd', '3rd', '4th', '5th', '6th', '7th', '8th',
'9th', '10th', '11th', '12th', '13th', '14th', '15th', '16th',
'17th', '18th', '19th', '20th', '21st', '22nd', '23rd', '24th',
'25th', '26th', '27th', '28th', '29th', '30th', '31st', '32nd',
'100th', '101st', '42042nd']
obs = [cardinal_to_ordinal(n) for n in
list(range(0, 33)) + [100, 101, 42042]]
self.assertEqual(obs, exp)
def _format_fasta_like_records(generator, id_whitespace_replacement, description_newline_replacement, require_qual):
if (id_whitespace_replacement is not None and "\n" in id_whitespace_replacement) or (
description_newline_replacement is not None and "\n" in description_newline_replacement
):
raise ValueError(
"Newline character (\\n) cannot be used to replace whitespace in "
"sequence IDs, nor to replace newlines in sequence descriptions."
)
for idx, seq in enumerate(generator):
if len(seq) < 1:
raise ValueError(
"%s sequence does not contain any characters (i.e., it is an "
"empty/blank sequence). Writing empty sequences is not "
"supported." % cardinal_to_ordinal(idx + 1)
)
id_ = seq.id
if id_whitespace_replacement is not None:
id_ = _whitespace_regex.sub(id_whitespace_replacement, id_)
desc = seq.description
if description_newline_replacement is not None:
desc = _newline_regex.sub(description_newline_replacement, desc)
if desc:
header = "%s %s" % (id_, desc)
else:
header = id_
if require_qual and seq.quality is None:
raise ValueError(
"Cannot write %s sequence because it does not have quality "
"scores associated with it." % cardinal_to_ordinal(idx + 1)
)
yield header, str(seq), seq.quality
def _format_fasta_like_records(generator, id_whitespace_replacement,
description_newline_replacement, require_qual):
if ((id_whitespace_replacement is not None and
'\n' in id_whitespace_replacement) or
(description_newline_replacement is not None and
'\n' in description_newline_replacement)):
raise ValueError(
"Newline character (\\n) cannot be used to replace whitespace in "
"sequence IDs, nor to replace newlines in sequence descriptions.")
for idx, seq in enumerate(generator):
if len(seq) < 1:
raise ValueError(
"%s sequence does not contain any characters (i.e., it is an "
"empty/blank sequence). Writing empty sequences is not "
"supported." % cardinal_to_ordinal(idx + 1))
id_ = seq.id
if id_whitespace_replacement is not None:
id_ = _whitespace_regex.sub(id_whitespace_replacement, id_)
desc = seq.description
if description_newline_replacement is not None:
desc = _newline_regex.sub(description_newline_replacement, desc)
if desc:
header = '%s %s' % (id_, desc)
else:
header = id_
if require_qual and not seq.has_quality():
raise ValueError(
"Cannot write %s sequence because it does not have quality "
"scores associated with it." % cardinal_to_ordinal(idx + 1))
yield header, seq.sequence, seq.quality
def _get_nth_sequence(generator, seq_num):
# i is set to None so that an empty generator will not result in an
# undefined variable when compared to seq_num.
i = None
if seq_num is None or seq_num < 1:
raise ValueError('Invalid sequence number (`seq_num`=%s). `seq_num`'
' must be between 1 and the number of sequences in'
' the file.' % str(seq_num))
try:
for i, seq in zip(range(1, seq_num + 1), generator):
pass
finally:
generator.close()
if i == seq_num:
return seq
raise ValueError('Reached end of file before finding the %s sequence.'
% cardinal_to_ordinal(seq_num))
def _get_nth_sequence(generator, seq_num):
# i is set to None so that an empty generator will not result in an
# undefined variable when compared to seq_num.
i = None
if seq_num is None or seq_num < 1:
raise ValueError('Invalid sequence number (`seq_num`=%s). `seq_num`'
' must be between 1 and the number of sequences in'
' the file.' % str(seq_num))
try:
for i, seq in zip(range(1, seq_num + 1), generator):
pass
finally:
generator.close()
if i == seq_num:
return seq
raise ValueError('Reached end of file before finding the %s sequence.'
% cardinal_to_ordinal(seq_num))
def test_valid_range(self):
# taken and modified from http://stackoverflow.com/a/20007730/3776794
exp = [
"0th",
"1st",
"2nd",
"3rd",
"4th",
"5th",
"6th",
"7th",
"8th",
"9th",
"10th",
"11th",
"12th",
"13th",
"14th",
"15th",
"16th",
"17th",
"18th",
"19th",
"20th",
"21st",
"22nd",
"23rd",
"24th",
"25th",
"26th",
"27th",
"28th",
"29th",
"30th",
"31st",
"32nd",
"100th",
"101st",
"42042nd",
]
obs = [cardinal_to_ordinal(n) for n in list(range(0, 33)) + [100, 101, 42042]]
self.assertEqual(obs, exp)
def _generator_to_fasta(obj, fh, id_whitespace_replacement='_',
description_newline_replacement=' ', max_width=None):
if ((id_whitespace_replacement is not None and
'\n' in id_whitespace_replacement) or
(description_newline_replacement is not None and
'\n' in description_newline_replacement)):
raise FASTAFormatError(
"Newline character (\\n) cannot be used to replace whitespace in "
"biological sequence IDs, nor to replace newlines in biological "
"sequence descriptions. Otherwise, the FASTA-formatted file will "
"be invalid.")
ws_pattern = re.compile(r'\s')
nl_pattern = re.compile(r'\n')
for idx, seq in enumerate(obj):
if len(seq) < 1:
raise FASTAFormatError(
"Cannot write %s biological sequence in FASTA format because "
"it does not contain any characters (i.e., it is an "
"empty/blank sequence). Empty sequences are not supported in "
"the FASTA file format." % cardinal_to_ordinal(idx + 1))
id_ = seq.id
if id_whitespace_replacement is not None:
id_ = re.sub(ws_pattern, id_whitespace_replacement, id_)
desc = seq.description
if description_newline_replacement is not None:
desc = re.sub(nl_pattern, description_newline_replacement, desc)
if desc:
header = '%s %s' % (id_, desc)
else:
header = id_
seq_str = str(seq)
if max_width is not None:
seq_str = _chunk_str(seq_str, max_width, '\n')
fh.write('>%s\n%s\n' % (header, seq_str))
def _fasta_to_sequence(fh, seq_num, constructor):
if seq_num < 1:
raise FASTAFormatError(
"Invalid sequence number (seq_num=%d). seq_num must be between 1 "
"and the number of sequences in the FASTA-formatted file "
"(inclusive)." % seq_num)
seq_idx = seq_num - 1
seq = None
try:
gen = _fasta_to_generator(fh, constructor=constructor)
for idx, curr_seq in enumerate(gen):
if idx == seq_idx:
seq = curr_seq
break
finally:
gen.close()
if seq is None:
raise FASTAFormatError(
"Reached end of FASTA-formatted file before finding %s biological "
"sequence." % cardinal_to_ordinal(seq_num))
return seq
def test_invalid_n(self):
with six.assertRaisesRegex(self, ValueError, '-1'):
cardinal_to_ordinal(-1)
def test_invalid_n(self):
with six.assertRaisesRegex(self, ValueError, '-1'):
cardinal_to_ordinal(-1)
def test_invalid_n(self):
with self.assertRaisesRegexp(ValueError, "-1"):
cardinal_to_ordinal(-1)
