class IdentifyFileFormat(DBTask):
queue = 'file_operation'
def handle_matches(self, fullname, matches, delta_t, matchtype=''):
if len(matches) == 0:
raise ValueError("No matches for %s" % fullname)
f, sigName = matches[-1]
self.lastFmt = f.find('name').text
def run(self, filename=None):
"""
Identifies the format of the file using the fido library
Args:
filename: The filename to identify
Returns:
The format of the file
"""
self.fid = Fido()
self.fid.handle_matches = self.handle_matches
self.fid.identify_file(filename)
self.set_progress(100, total=100)
return self.lastFmt
def undo(self, filename=None):
pass
def event_outcome_success(self, filename=None, block_size=65536, algorithm='SHA-256'):
return "Identified format of %s" % filename
def test_fido_cache_halting_file(fido_cache_halting_file):
"""Tests that time used between raw Fido usage and FidoDetector usage does
not provide big difference in processing time."""
fido_object = Fido(
quiet=True, format_files=["formats-v95.xml", "format_extensions.xml"])
fido_start_time = time.time()
fido_object.identify_file(fido_cache_halting_file)
fido_elapsed_time = time.time() - fido_start_time
fido_reader_start_time = time.time()
fido_reader_object = FidoDetector(fido_cache_halting_file)
fido_reader_object.detect()
fido_reader_elapsed_time = time.time() - fido_reader_start_time
# 2 second difference is acceptable with the given test file.
assert abs(fido_elapsed_time - fido_reader_elapsed_time) < 2
class FormatIdentification():
"""
File Format Identification
"""
def __init__(self):
self.fid = Fido()
self.fid.handle_matches = self.print_matches
self.lastFmt = None
def identify_file(self, entry):
"""
This function identifies the file format of every file that is handed over.
"""
self.fid.identify_file(entry)
return self.lastFmt
def print_matches(self, fullname, matches, delta_t, matchtype=''):
#print "####" + fullname
for (f, s) in matches:
self.lastFmt = self.fid.get_puid(f)
class FormatIdentification():
"""
File Format Identification
"""
def __init__(self):
self.fid = Fido()
self.fid.handle_matches = self.print_matches
self.lastFmt = None
def identify_file(self, entry):
"""
This function identifies the file format of every file that is handed over.
"""
self.fid.identify_file(entry)
return self.lastFmt
def get_mime_for_puid(self, puid):
"""
Get mime type for a given puid
@type puid: string
@param puid: PRONOM Persistent Unique Identifier
@rtype: string
@return: mime type string (default: application/octet-stream)
"""
mime_tag = "mime"
fmtres = self.fid.puid_format_map[puid]
childs = [child for child in fmtres if child.tag.endswith(mime_tag)]
if len(childs) == 1:
return (childs[0]).text.strip()
else:
return "application/octet-stream"
def print_matches(self, fullname, matches, delta_t, matchtype=''):
# print "####" + fullname
for (f, s) in matches:
self.lastFmt = self.fid.get_puid(f)
class FormatIdentification():
"""
File Format Identification
"""
def __init__(self):
if not fido_disabled:
self.fid = Fido()
self.fid.handle_matches = self.print_matches
self.lastFmt = None
def identify_file(self, entry):
"""
This function identifies the file format of every file that is handed over.
"""
assert not fido_disabled, "Fido module is not available!"
self.fid.identify_file(entry)
return self.lastFmt
def get_mime_for_puid(self, puid):
"""
:param puid: PRONOM Persistent Unique Identifier
:return: mime type string (default: application/octet-stream)
"""
assert not fido_disabled, "Fido module is not available!"
mime_tag = "mime"
fmtres = self.fid.puid_format_map[puid]
childs = [child for child in fmtres if child.tag.endswith(mime_tag)]
if len(childs) == 1:
return (childs[0]).text.strip()
return "application/octet-stream"
def print_matches(self, fullname, matches, delta_t, matchtype=''):
assert not fido_disabled, "Fido module is not available!"
for (f, s) in matches:
self.lastFmt = self.fid.get_puid(f)
