def __init__(
self, name, sequence, qualities, primer=None, name2='',
original_length=None, match=None, match_info=None, clipped=None,
insert_overlap=False, merged=False, corrected=0, alphabet=None):
# In colorspace, the first character is the last nucleotide of the
# primer base and the second character encodes the transition from the
# primer base to the first real base of the read.
if primer is None:
self.primer = sequence[0:1]
sequence = sequence[1:]
else:
self.primer = primer
if qualities is not None and len(sequence) != len(qualities):
rname = truncate_string(name)
raise FormatError(
"In read named {0!r}: length of colorspace quality "
"sequence ({1}) and length of read ({2}) do not match (primer "
"is: {3!r})".format(
rname, len(qualities), len(sequence), self.primer))
super().__init__(
name, sequence, qualities, name2, original_length, match,
match_info, clipped, insert_overlap, merged, corrected,
alphabet=alphabet)
# TODO: use 'alphabet' here
if not self.primer in ('A', 'C', 'G', 'T'):
raise FormatError(
"Primer base is {0!r} in read {1!r}, but it should be one of "
"A, C, G, T.".format(self.primer, truncate_string(name)))
def __repr__(self):
fmt_str = \
'<ColorspaceSequence(name={0!r}, primer={1!r}, sequence={2!r}{3})>'
qstr = ''
if self.qualities is not None:
qstr = ', qualities={0!r}'.format(truncate_string(self.qualities))
return fmt_str.format(truncate_string(self.name), self.primer,
truncate_string(self.sequence), qstr)
def __repr__(self):
fmt_str = \
'<ColorspaceSequence(name={0!r}, primer={1!r}, sequence={2!r}{3})>'
qstr = ''
if self.qualities is not None:
qstr = ', qualities={0!r}'.format(truncate_string(self.qualities))
return fmt_str.format(
truncate_string(self.name), self.primer,
truncate_string(self.sequence), qstr)
def __iter__(self):
"""Read next entry from the file (single entry at a time).
"""
name = None
seq = []
for i, line in enumerate(self._file):
# strip() also removes DOS line breaks
line = line.strip()
if not line:
continue
if line and line[0] == '>':
if name is not None:
yield self.sequence_class(
name, self._delimiter.join(seq), None,
alphabet=self.alphabet)
name = line[1:]
seq = []
elif line and line[0] == '#':
continue
elif name is not None:
seq.append(line)
else:
raise FormatError(
"At line {0}: Expected '>' at beginning of FASTA record, "
"but got {1!r}.".format(i+1, truncate_string(line)))
if name is not None:
yield self.sequence_class(
name, self._delimiter.join(seq), None,
alphabet=self.alphabet)
def __iter__(self):
"""Read next entry from the file (single entry at a time).
"""
name = None
seq = []
for i, line in enumerate(self._file):
# strip() also removes DOS line breaks
line = line.strip()
if not line:
continue
if line and line[0] == '>':
if name is not None:
yield self.sequence_class(name,
self._delimiter.join(seq),
None,
alphabet=self.alphabet)
name = line[1:]
seq = []
elif line and line[0] == '#':
continue
elif name is not None:
seq.append(line)
else:
raise FormatError(
"At line {0}: Expected '>' at beginning of FASTA record, "
"but got {1!r}.".format(i + 1, truncate_string(line)))
if name is not None:
yield self.sequence_class(name,
self._delimiter.join(seq),
None,
alphabet=self.alphabet)
def __init__(self,
name,
sequence,
qualities,
primer=None,
name2='',
original_length=None,
match=None,
match_info=None,
clipped=None,
insert_overlap=False,
merged=False,
corrected=0,
alphabet=None):
# In colorspace, the first character is the last nucleotide of the
# primer base and the second character encodes the transition from the
# primer base to the first real base of the read.
if primer is None:
self.primer = sequence[0:1]
sequence = sequence[1:]
else:
self.primer = primer
if qualities is not None and len(sequence) != len(qualities):
rname = truncate_string(name)
raise FormatError(
"In read named {0!r}: length of colorspace quality "
"sequence ({1}) and length of read ({2}) do not match (primer "
"is: {3!r})".format(rname, len(qualities), len(sequence),
self.primer))
super().__init__(name,
sequence,
qualities,
name2,
original_length,
match,
match_info,
clipped,
insert_overlap,
merged,
corrected,
alphabet=alphabet)
# TODO: use 'alphabet' here
if not self.primer in ('A', 'C', 'G', 'T'):
raise FormatError(
"Primer base is {0!r} in read {1!r}, but it should be one of "
"A, C, G, T.".format(self.primer, truncate_string(name)))
def __call__(self,
*args,
colwidths=None,
extra_width=None,
justification=None,
extra_justification=None,
indent=None,
extra_indent=None,
header=False,
underline='-',
pct=None,
default=None,
**kwargs):
"""Print a row.
Args:
args: Fields in the row.
colwidths, justification, indent: Row-specific colwidths,
justification, indent.
extra_width, extra_justification, extra_indent: colwidth/
justification/indent to use for extra fields.
header: Whether this is a header row.
underline: Whether to use an underline after the header row. Either
a bool or a character.
pct: Whether floating point values should be formatted as
percentages.
default: Default value.
kwargs: Additional keyword arguments to pass to print.
"""
ncols = len(args)
if ncols == 0:
self.newline()
return
if pct is None:
pct = self.pct
def adjust(arr, extra=None):
"""Adjust an array. If longer than the number of columns,
truncate; if shorter, fill in by repeating the last element.
"""
alen = len(arr)
if alen == ncols:
return arr
elif alen > ncols:
return arr[:ncols]
else:
return arr + ((extra or arr[-1], ) * (ncols - alen))
colwidths, justification, indent = (adjust(
arr, extra) for arr, extra in zip((
colwidths or self.colwidths,
justification or self.justification,
indent or self.indent), (extra_width, extra_justification,
extra_indent)))
# adjust colwidths if this is a header
if header:
colwidths = tuple(
max(w, len(str(a))) for w, a in zip(colwidths, args))
fmt_str = []
fmt_args = []
for i, (value, width, just,
ind) in enumerate(zip(args, colwidths, justification, indent)):
if value is None:
value = default or self.default
if isinstance(value, str):
typ = 's'
if len(value) > width:
value = truncate_string(value, width)
elif isinstance(value, float):
typ = ',.1' + ('%' if pct else 'f')
else:
typ = ',d'
fmt_str.append(ind + '{' + str(i) + ':' + just +
str(width - len(ind)) + typ + '}')
fmt_args.append(value)
fmt_str = ' '.join(fmt_str)
self._print(fmt_str.format(*fmt_args), **kwargs)
if header:
sepline = ' '.join((underline * width) for width in colwidths)
self._print(sepline, **kwargs)
def __call__(
self, *args, colwidths=None, extra_width=None, justification=None,
extra_justification=None, indent=None, extra_indent=None,
header=False, underline='-', pct=None, default=None, **kwargs):
"""Print a row.
Args:
args: Fields in the row.
colwidths, justification, indent: Row-specific colwidths,
justification, indent.
extra_width, extra_justification, extra_indent: colwidth/
justification/indent to use for extra fields.
header: Whether this is a header row.
underline: Whether to use an underline after the header row. Either
a bool or a character.
pct: Whether floating point values should be formatted as
percentages.
default: Default value.
kwargs: Additional keyword arguments to pass to print.
"""
ncols = len(args)
if ncols == 0:
self.newline()
return
if pct is None:
pct = self.pct
def adjust(arr, extra=None):
"""Adjust an array. If longer than the number of columns,
truncate; if shorter, fill in by repeating the last element.
"""
alen = len(arr)
if alen == ncols:
return arr
elif alen > ncols:
return arr[:ncols]
else:
return arr + ((extra or arr[-1],) * (ncols - alen))
colwidths, justification, indent = (
adjust(arr, extra)
for arr, extra in zip(
(
colwidths or self.colwidths,
justification or self.justification,
indent or self.indent),
(extra_width, extra_justification, extra_indent)))
# adjust colwidths if this is a header
if header:
colwidths = tuple(
max(w, len(str(a)))
for w, a in zip(colwidths, args))
fmt_str = []
fmt_args = []
for i, (value, width, just, ind) in enumerate(
zip(args, colwidths, justification, indent)):
if value is None:
value = default or self.default
if isinstance(value, str):
typ = 's'
if len(value) > width:
value = truncate_string(value, width)
elif isinstance(value, float):
typ = ',.1' + ('%' if pct else 'f')
else:
typ = ',d'
fmt_str.append(
ind + '{' + str(i) + ':' + just + str(width-len(ind)) +
typ + '}')
fmt_args.append(value)
fmt_str = ' '.join(fmt_str)
self._print(fmt_str.format(*fmt_args), **kwargs)
if header:
sepline = ' '.join((underline * width) for width in colwidths)
self._print(sepline, **kwargs)