def _blast6_to_data_frame(fh, columns=None, default_columns=False):
if default_columns and columns is not None:
raise ValueError("`columns` and `default_columns` cannot both be" " provided.")
if not default_columns and columns is None:
raise ValueError("Either `columns` or `default_columns` must be" " provided.")
if default_columns:
columns = _default_columns
else:
for column in columns:
if column not in _possible_columns:
raise ValueError(
"Unrecognized column (%r)." " Supported columns:\n%r" % (column, set(_possible_columns.keys()))
)
return _parse_blast_data(
fh, columns, ValueError, "Specified number of columns (%r) does not equal" " number of columns in file (%r)."
)
def _blast6_to_data_frame(fh, columns=None, default_columns=False):
if default_columns and columns is not None:
raise ValueError("`columns` and `default_columns` cannot both be"
" provided.")
if not default_columns and columns is None:
raise ValueError("Either `columns` or `default_columns` must be"
" provided.")
if default_columns:
columns = _default_columns
else:
for column in columns:
if column not in _possible_columns:
raise ValueError("Unrecognized column (%r)."
" Supported columns:\n%r" %
(column, set(_possible_columns.keys())))
return _parse_blast_data(fh, columns, ValueError,
"Specified number of columns (%r) does not equal"
" number of columns in file (%r).")
def _blast7_to_data_frame(fh):
line_num = 0
columns = None
skiprows = []
for line in fh:
if line == "# Fields: \n":
# Identifies Legacy BLAST 9 data
line = next(fh)
line_num += 1
if columns is None:
columns = _parse_fields(line, legacy=True)
skiprows.append(line_num)
else:
next_columns = _parse_fields(line, legacy=True)
if columns != next_columns:
raise BLAST7FormatError(
"Fields %r do not equal fields %r" %
(columns, next_columns))
skiprows.append(line_num)
elif line.startswith("# Fields: "):
# Identifies BLAST+7 data
if columns is None:
columns = _parse_fields(line)
else:
# Affirms data types do not differ throught file
next_columns = _parse_fields(line)
if columns != next_columns:
raise BLAST7FormatError(
"Fields %r do not equal fields %r" %
(columns, next_columns))
line_num += 1
if columns is None:
# Affirms file contains BLAST data
raise BLAST7FormatError("File contains no BLAST data.")
fh.seek(0)
return _parse_blast_data(fh,
columns,
BLAST7FormatError,
"Number of fields (%r) does not equal number"
" of data columns (%r).",
comment='#',
skiprows=skiprows)
def _blast7_to_data_frame(fh):
line_num = 0
columns = None
skiprows = []
for line in fh:
if line == "# Fields: \n":
# Identifies Legacy BLAST 9 data
line = next(fh)
line_num += 1
if columns is None:
columns = _parse_fields(line, legacy=True)
skiprows.append(line_num)
else:
next_columns = _parse_fields(line, legacy=True)
if columns != next_columns:
raise BLAST7FormatError("Fields %r do not equal fields %r"
% (columns, next_columns))
skiprows.append(line_num)
elif line.startswith("# Fields: "):
# Identifies BLAST+7 data
if columns is None:
columns = _parse_fields(line)
else:
# Affirms data types do not differ throught file
next_columns = _parse_fields(line)
if columns != next_columns:
raise BLAST7FormatError("Fields %r do not equal fields %r"
% (columns, next_columns))
line_num += 1
if columns is None:
# Affirms file contains BLAST data
raise BLAST7FormatError("File contains no BLAST data.")
fh.seek(0)
return _parse_blast_data(fh, columns, BLAST7FormatError,
"Number of fields (%r) does not equal number"
" of data columns (%r).", comment='#',
skiprows=skiprows)