def _next(self, line):
if len(line)>0 and line[0]=='#':
return None
origCols = line.split('\t')
cols = [unquote(x) for x in origCols]
if len(cols) != 9:
raise InvalidFormatError("Error: GFF files must contain 9 tab-separated columns")
ge = GenomeElement(self._genome)
ge.chr = self._checkValidChr(cols[0])
ge.source = cols[1]
ge.type = cols[2]
ge.start = self._checkValidStart(ge.chr, int(cols[3]) - 1)
ge.end = self._checkValidEnd(ge.chr, int(cols[4]), start=ge.start)
ge.val = numpy.float(self._handleNan(cols[5]))
ge.strand = self._getStrandFromString(cols[6])
ge.phase = cols[7]
ge.attributes = cols[8]
for attr in origCols[8].split(';'):
attrSplitted = attr.split('=')
if len(attrSplitted) == 2:
key, val = attrSplitted
if key.lower() == 'id':
ge.id = unquote(val)
elif key.lower() == 'name':
ge.name = unquote(val)
return ge
def _next(self, line):
if line.startswith('#'):
return
ge = GenomeElement(self._genome)
cols = line.split('\t')
if self._numCols is not None:
if len(cols) != self._numCols:
raise InvalidFormatError('Error: BED files must have the same number of columns in each data line.')
else:
self._numCols = len(cols)
if self._numCols < self.MIN_NUM_COLS or self._numCols > self.MAX_NUM_COLS:
raise InvalidFormatError('Error: BED file must contain between %s and %s columns.' % (self.MIN_NUM_COLS, self.MAX_NUM_COLS))
ge.chr = self._checkValidChr(cols[0])
ge.start = self._checkValidStart(ge.chr, int(cols[1]))
self._parseEnd( ge, self._checkValidEnd(ge.chr, int(cols[2]), start=ge.start))
self._parseName( ge, cols )
self._parseVal( ge, cols )
if self._numCols >= 6:
ge.strand = self._getStrandFromString(cols[5])
for i,extraCol in enumerate(self.BED_EXTRA_COLUMNS):
if self._numCols >= i+7:
setattr(ge, extraCol, cols[i+6])
return ge
def _next(self, line):
cols = line.split('\t')
ge = GenomeElement(self._genome)
ge.chr = self._checkValidChr(cols[0])
ge.start = int(cols[1])
ge.end = int(cols[2])
self._parseVal(ge, cols[3])
return ge
def _next(self, line):
cols = line.split('\t')
ge = GenomeElement(self._genome)
ge.chr = self._checkValidChr(cols[0])
ge.start = int(cols[1])
ge.end = int(cols[2])
self._parseVal(ge, cols[3])
return ge
def _next(self, line):
if line.startswith('##FASTA'):
raise StopIteration
if len(line) > 0 and line[0] == '#':
return None
origCols = line.split('\t')
cols = [unquote(x) for x in origCols]
if len(cols) != 9:
raise InvalidFormatError(
"Error: GFF files must contain 9 tab-separated columns")
ge = GenomeElement(self._genome)
ge.chr = self._checkValidChr(cols[0])
ge.source = cols[1]
self._parseThirdCol(ge, cols[2])
ge.start = self._checkValidStart(ge.chr, int(cols[3]) - 1)
ge.end = self._checkValidEnd(ge.chr, int(cols[4]), start=ge.start)
self._parseSixthCol(ge, cols[5])
ge.strand = self._getStrandFromString(cols[6])
ge.phase = cols[7]
ge.attributes = cols[8]
for attr in origCols[8].split(';'):
attrSplitted = attr.split('=')
if len(attrSplitted) == 2:
key, val = attrSplitted
if key.lower() == 'id':
ge.id = unquote(val)
elif key.lower() == 'name':
ge.name = unquote(val)
return ge
