def detect(self):
"""Detect charset with MagicLib. A charset is detected from up to
1 megabytes of data from the beginning of file."""
messages = []
errors = []
charset = magic_analyze(MAGIC_LIB, MAGIC_LIB.MAGIC_MIME_ENCODING,
self.filename)
if charset is None or charset.upper() == "BINARY":
errors.append("Unable to detect character encoding.")
elif charset.upper() == "US-ASCII":
self.charset = "UTF-8"
elif charset.upper() == "ISO-8859-1":
self.charset = "ISO-8859-15"
elif charset.upper() == "UTF-16LE" or \
charset.upper() == "UTF-16BE":
self.charset = "UTF-16"
else:
self.charset = charset.upper()
if not errors:
messages.append("Character encoding detected as %s" % self.charset)
self.info = {
"class": self.__class__.__name__,
"messages": messages,
"errors": errors,
"tools": []
}
def detect(self):
"""Detect mimetype."""
mimetype = magic_analyze(MAGIC_LIB, MAGIC_LIB.MAGIC_MIME_TYPE,
self.filename)
if mimetype in MIMETYPE_DICT:
self.mimetype = MIMETYPE_DICT[mimetype]
else:
self.mimetype = six.text_type(mimetype)
self.info = {"class": self.__class__.__name__,
"messages": [],
"errors": []}
def _magic_call(self):
"""Fetch three values from file with using magic.
These are: mimetype, info line (for version) and encoding.
:returns: Python dict of the three fetched values from magic
"""
magicdict = {
"magic_mime_type": MAGIC_LIB.MAGIC_MIME_TYPE,
"magic_none": MAGIC_LIB.MAGIC_NONE,
"magic_mime_encoding": MAGIC_LIB.MAGIC_MIME_ENCODING
}
magic_result = {}
for key, value in magicdict.items():
magic_result[key] = magic_analyze(MAGIC_LIB, value, self.filename)
return magic_result