def guess_file_type(filename):
"""Attempt to guess the type of the input file.
Args:
filename: A string, the name of the file to guess the type for.
Returns:
A suitable mimetype string, or None if we could not guess.
"""
warnings.warn(
'beangulp.file_type.guess_file_type() is deprecated. '
'Use the beangulp.mimetypes module instead.',
DeprecationWarning,
stacklevel=2)
filetype, encoding = mimetypes.guess_type(filename, strict=False)
if filetype:
return filetype
if magic:
filetype = magic.from_file(filename, mime=True)
if isinstance(filetype, bytes):
filetype = filetype.decode('utf8')
return filetype
def mimetype(filename):
"""A converter that computes the MIME type of the file.
Returns:
A converter function.
"""
mtype, _ = mimetypes.guess_type(filename, strict=False)
return mtype
def identify(self, filepath):
mimetype, encoding = mimetypes.guess_type(filepath)
if mimetype != 'text/csv':
return False
with open(filepath) as fd:
head = fd.read(1024)
return head.startswith('Details,Posting Date,"Description",'
'Amount,Type,Balance,Check or Slip #,')
def identify(self, filepath):
mimetype, encoding = mimetypes.guess_type(filepath)
if mimetype != 'application/pdf':
return False
# Look for some words in the PDF file to figure out if it's a statement
# from ACME. The filename they provide (Statement.pdf) isn't useful.
text = pdf_to_text(filepath)
if text:
return re.match('ACME Bank', text) is not None
def is_mimetype(filepath: str,
check_mimetypes: Union[str, Set[str]],
regexp: Optional[bool] = False) -> bool:
"""Check if a file is of one of many mimetypes."""
if isinstance(check_mimetypes, str):
check_mimetypes = set((check_mimetypes, ))
mtype, _ = mimetypes.guess_type(filepath)
if mtype is None:
return False
return (any(re.fullmatch(r, mtype)
for r in check_mimetypes) if not regexp else
(mtype in check_mimetypes))
def identify(self, filepath):
# Match for a compatible MIME type.
if mimetypes.guess_type(filepath) not in {
'application/x-ofx', 'application/vnd.intu.qbo',
'application/vnd.intu.qfx'
}:
return False
# Match the account id.
with open(filepath) as fd:
contents = fd.read()
return any(
re.match(self.acctid_regexp, acctid)
for acctid in find_acctids(contents))
def identify(self, filepath):
mimetype, encoding = mimetypes.guess_type(filepath, False)
return mimetype == self._mimetype