def sniff_prefix(self, file_prefix: FilePrefix):
"""
Determines whether the file is an amos assembly file format
Example::
{CTG
iid:1
eid:1
seq:
CCTCTCCTGTAGAGTTCAACCGA-GCCGGTAGAGTTTTATCA
.
qlt:
DDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDDD
.
{TLE
src:1027
off:0
clr:618,0
gap:
250 612
.
}
}
"""
for line in file_prefix.line_iterator():
if not line:
break # EOF
line = line.strip()
if line: # first non-empty line
if line.startswith('{'):
if re.match(r'{(RED|CTG|TLE)$', line):
return True
return False
def _has_root_element_in_prefix(self, file_prefix: FilePrefix, root):
for line in file_prefix.line_iterator():
if not line.startswith('<?'):
break
# pattern match <root or <ns:root for any ns string
pattern = r'^<(\w*:)?%s' % root
return re.match(pattern, line) is not None
def sniff_prefix(self, file_prefix: FilePrefix):
"""Each file must have one or more data blocks.
The start of a data block is defined by the keyword
"data_" followed by an optional string for
identification (e.g., "data_images"). All text
before the first "data_" keyword are comments
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname('1.star')
>>> Star().sniff(fname)
True
>>> fname = get_test_fname('interval.interval')
>>> Star().sniff(fname)
False
"""
in_data_block = False
for line in file_prefix.line_iterator():
# All lines before the first
# data_ block must be comments.
line = line.strip()
if len(line) == 0:
continue
if line.startswith("data_"):
in_data_block = True
continue
if in_data_block:
# Lines within data blocks must
# be blank, start with loop_, or
# start with _.
if len(line) == 0:
continue
if line.startswith("loop_") or line.startswith("_"):
return True
return False
return False
def sniff_prefix(self, file_prefix: FilePrefix):
""" Determines whether the file is the correct XML type. """
for line in file_prefix.line_iterator():
line = line.strip()
if not line.startswith('<?'):
break
# pattern match <root or <ns:root for any ns string
pattern = r'<(\w*:)?%s' % self.root
return re.search(pattern, line) is not None
def sniff_prefix(self, file_prefix: FilePrefix):
"""
Checking for keyword - 'Collection' or 'Image' in the first 200 lines.
>>> from galaxy.datatypes.sniff import get_test_fname
>>> fname = get_test_fname('1.dzi')
>>> Dzi().sniff(fname)
True
>>> fname = get_test_fname('megablast_xml_parser_test1.blastxml')
>>> Dzi().sniff(fname)
False
"""
for line in file_prefix.line_iterator():
line = line.lower()
if line.find('<collection') >= 0 or line.find('<image') >= 0:
return True
return False
def sniff_prefix(self, file_prefix: FilePrefix):
sep = None
header = None
for idx, line in enumerate(file_prefix.line_iterator()):
line = line.strip()
if sep is None:
sep = self._parse_delimiter(line)
if sep is None:
return False
line = line.split(sep)
if len(line) != 3:
return False
if idx == 0:
header = self._parse_header(line)
if (header is None) and not self._parse_dataline(line):
return False
elif not self._parse_dataline(line):
return False
if sep is None or header is None:
return False
return True
def sniff_prefix(self, file_prefix: FilePrefix):
sep = None
tpe = None
for idx, line in enumerate(file_prefix.line_iterator()):
line = line.strip("\r\n")
if sep is None:
sep = self._parse_delimiter(line)
if sep is None:
return False
line = line.split(sep)
if idx == 0:
tpe = self._parse_type(line)
if tpe is None:
return False
elif tpe == 0 and not self._parse_dataline(line, tpe):
return False
elif not self._parse_dataline(line, tpe):
return False
if tpe is None:
return False
return True
def sniff_prefix(self, file_prefix: FilePrefix):
""" Determines whether the file is a valid ms2 file."""
header_lines = []
for line in file_prefix.line_iterator():
if line.strip() == "":
continue
elif line.startswith('H\t'):
header_lines.append(line)
else:
break
for header_field in [
'CreationDate', 'Extractor', 'ExtractorVersion',
'ExtractorOptions'
]:
found_header = False
for header_line in header_lines:
if header_line.startswith(f'H\t{header_field}'):
found_header = True
break
if not found_header:
return False
return True