def calculate_difference(preview, original_image_id):
"""Calculate difference between two images.
@param preview: preview dict
@param original_image_id: original image ID
@return: difference, difference percentage
"""
try:
i1 = utils.str2image(get_file(original_image_id).read())
except IOError as e:
logger.warning("Comparer error reading image: {0}".format(e))
return
# Check if thumb was resized.
if "original_file" in preview:
i2 = utils.str2image(get_file(preview["original_file"]).read())
else:
i2 = utils.str2image(get_file(preview["file"]).read())
# Resize.
width, height = i2.size
try:
i1 = i1.resize([width, height], Image.ANTIALIAS)
except IOError as e:
logger.warning("Comparer error reading image: {0}".format(e))
return
# Checks.
#assert i1.mode == i2.mode, "Different kinds of images."
#assert i1.size == i2.size, "Different sizes."
# Calculate difference.
pairs = izip(i1.getdata(), i2.getdata())
if len(i1.getbands()) == 1:
# for gray-scale jpegs
dif = sum(abs(p1 - p2) for p1, p2 in pairs)
else:
dif = sum(
abs(c1 - c2) for p1, p2 in pairs for c1, c2 in zip(p1, p2))
ncomponents = i1.size[0] * i1.size[1] * 3
# Get diff percentage.
diff_perc = int((dif / 255.0 * 100) / ncomponents)
# Binary option.
if diff_perc >= 15:
diff = True
else:
diff = False
return diff, diff_perc
def calculate_difference(preview, original_image_id):
"""Calculate difference between two images.
@param preview: preview dict
@param original_image_id: original image ID
@return: difference, difference percentage
"""
try:
i1 = utils.str2image(get_file(original_image_id).read())
except IOError as e:
logger.warning("Comparer error reading image: {0}".format(e))
return
# Check if thumb was resized.
if "original_file" in preview:
i2 = utils.str2image(get_file(preview["original_file"]).read())
else:
i2 = utils.str2image(get_file(preview["file"]).read())
# Resize.
width, height = i2.size
try:
i1 = i1.resize([width, height], Image.ANTIALIAS)
except IOError as e:
logger.warning("Comparer error reading image: {0}".format(e))
return
# Checks.
# assert i1.mode == i2.mode, "Different kinds of images."
# assert i1.size == i2.size, "Different sizes."
# Calculate difference.
pairs = izip(i1.getdata(), i2.getdata())
if len(i1.getbands()) == 1:
# for gray-scale jpegs
dif = sum(abs(p1 - p2) for p1, p2 in pairs)
else:
dif = sum(abs(c1 - c2) for p1, p2 in pairs for c1, c2 in zip(p1, p2))
ncomponents = i1.size[0] * i1.size[1] * 3
# Get diff percentage.
diff_perc = int((dif / 255.0 * 100) / ncomponents)
# Binary option.
if diff_perc >= 15:
diff = True
else:
diff = False
return diff, diff_perc
def __init__(self, mongo_id, file_name=None):
# Results storage.
self.results = AutoVivification()
# Store image id.
if mongo_id:
self.orig_id = mongo_id
else:
raise Exception("You have to pass the original image ID")
if file_name:
self.file_name = file_name
else:
self.file_name = None
# Read image data.
try:
self.file_data = get_file(self.orig_id).read()
except gridfs.errors.NoFile:
raise Exception("Image not found on GridFS storage")
# Save a temporary file, used for analysis which needs a file on disk.
temp_image = tempfile.NamedTemporaryFile(delete=False)
temp_image.write(self.file_data)
temp_image.close(
) # File is not immediately deleted because we used delete=False
self.temp_image = temp_image.name
def hexview(image_id, length=8):
"""Hexdump representation.
@param image_id: gridfs image id
@return: hexdump
@see: code inspired to http://code.activestate.com/recipes/142812/
"""
# Get image from gridfs.
try:
file = get_file(image_id)
except (InvalidId, TypeError):
return None
# Read data.
src = file.read()
hex_dump = []
# Deal with unicode.
if isinstance(src, unicode):
digits = 4
else:
digits = 2
# Create hex view.
for i in xrange(0, len(src), length):
line = {}
s = src[i:i + length]
hexa = b" ".join(["%0*X" % (digits, ord(x)) for x in s])
text = b"".join([x if 0x20 <= ord(x) < 0x7F else b"." for x in s])
line["address"] = b"%04X" % i
line["hex"] = b"%-*s" % (length * (digits + 1), hexa)
line["text"] = text
hex_dump.append(line)
return hex_dump
def __init__(self, mongo_id, file_name=None):
# Results storage.
self.results = AutoVivification()
# Store image id.
if mongo_id:
self.orig_id = mongo_id
else:
raise Exception("You have to pass the original image ID")
if file_name:
self.file_name = file_name
else:
self.file_name = None
# Read image data.
try:
self.file_data = get_file(self.orig_id).read()
except gridfs.errors.NoFile:
raise Exception("Image not found on GridFS storage")
# Save a temporary file, used for analysis which needs a file on disk.
temp_image = tempfile.NamedTemporaryFile(delete=False)
temp_image.write(self.file_data)
temp_image.close() # File is not immediately deleted because we used delete=False
self.temp_image = temp_image.name
def handle(self, *args, **options):
print("Starting")
if os.path.exists(options["path"]):
dst_path = os.path.join(options["path"], "ghiro_output")
if os.path.exists(dst_path):
print "ERROR: a folder 'ghiro_output' already exist in that path!"
sys.exit()
else:
# Create destination folder.
os.mkdir(dst_path)
# We are fine, run!
for analysis in Analysis.objects.all():
try:
file = get_file(analysis.image_id)
except (InvalidId, TypeError) as e:
print("Unable to dump %s: %s" % (analysis.id, e))
continue
else:
with open(
os.path.join(dst_path,
"analysis_%s" % analysis.id),
"a") as the_file:
the_file.write(file.read())
else:
print("ERROR: path not found!")
def hexdump(image_id, length=8):
"""Hexdump representation.
@param image_id: gridfs image id
@return: hexdump
@see: code inspired to http://code.activestate.com/recipes/142812/
"""
# Get image from gridfs.
try:
file = get_file(image_id)
except (InvalidId, TypeError):
return None
# Read data.
src = file.read()
hex_dump = []
# Deal with unicode.
if isinstance(src, unicode):
digits = 4
else:
digits = 2
# Create hex view.
for i in xrange(0, len(src), length):
line = {}
s = src[i:i+length]
hexa = b" ".join(["%0*X" % (digits, ord(x)) for x in s])
text = b"".join([x if 0x20 <= ord(x) < 0x7F else b"." for x in s])
line["address"] = b"%04X" % i
line["hex"] = b"%-*s" % (length*(digits + 1), hexa)
line["text"] = text
hex_dump.append(line)
return hex_dump
def handle(self, *args, **options):
print "Starting"
if os.path.exists(options["path"]):
dst_path = os.path.join(options["path"], "ghiro_output")
if os.path.exists(dst_path):
print "ERROR: a folder 'ghiro_output' already exist in that path!"
sys.exit()
else:
# Create destination folder.
os.mkdir(dst_path)
# Mongo connection.
db = mongo_connect()
fs = gridfs.GridFS(db)
# We are fine, run!
for analysis in Analysis.objects.all():
try:
file = get_file(analysis.image_id)
except (InvalidId, TypeError) as e:
print "Unable to dump %s: %s" % (analysis.id, e)
continue
else:
with open(os.path.join(dst_path, "analysis_%s" % analysis.id), "a") as the_file:
the_file.write(file.read())
else:
print "ERROR: path not found!"
def handle(self, *args, **options):
print "Starting"
if os.path.exists(options["path"]):
dst_path = os.path.join(options["path"], "ghiro_output")
if os.path.exists(dst_path):
print "ERROR: a folder 'ghiro_output' already exist in that path!"
sys.exit()
else:
# Mongo connection.
db = mongo_connect()
fs = gridfs.GridFS(db)
# We are fine, run!
for analysis in Analysis.objects.all():
try:
file = get_file(analysis.image_id)
except (InvalidId, TypeError):
print "Unable to dump %s" % analysis.id
continue
else:
with open(
os.path.join(dst_path,
"analysis_%s" % analysis.id),
"a") as the_file:
the_file.write(file)
else:
print "ERROR: path not found!"
def to_base64(image_id):
"""Return a base64 representation for an image to be used in html img tag.
@param image_id: mongo gridfs id
@return: base64 blob
"""
image_obj = get_file(image_id)
image_encoded = base64.encodestring(image_obj.read())
return "data:%s;base64,%s" % (image_obj.content_type, image_encoded)
def to_base64(image_id):
"""Return a base64 representation for an image to be used in html img tag.
@param image_id: mongo gridfs id
@return: base64 blob
"""
image_obj = get_file(image_id)
image_encoded = base64.encodestring(image_obj.read())
return "data:%s;base64,%s" % (image_obj.content_type, image_encoded)
def to_strings(image_id):
"""Extract all strings.
@param image_id: mongo gridfs id
@return: strings list
"""
data = get_file(image_id).read()
# This strings extraction code comes form Cuckoo Sandbox.
strings = re.findall("[\x1f-\x7e]{6,}", data)
strings += [str(ws.decode("utf-16le")) for ws in re.findall("(?:[\x1f-\x7e][\x00]){6,}", data)]
return strings
def to_strings(image_id):
"""Extract all strings.
@param image_id: mongo gridfs id
@return: strings list
"""
data = get_file(image_id).read()
# This strings extraction code comes form Cuckoo Sandbox.
strings = re.findall("[\x1f-\x7e]{6,}", data)
strings += [str(ws.decode("utf-16le")) for ws in re.findall("(?:[\x1f-\x7e][\x00]){6,}", data)]
return strings
def image(request, id):
try:
file = get_file(id)
except (InvalidId, TypeError):
return render_to_response("error.html",
{"error": "Unable to load image."},
context_instance=RequestContext(request))
data = file.read()
response = HttpResponse(data, content_type=file.content_type)
response["Content-Disposition"] = "attachment; filename=%s" % id
response["Content-Length"] = len(data)
return response
def image(request, id):
try:
file = get_file(id)
except (InvalidId, TypeError):
return render_to_response("error.html",
{"error": "Unable to load image."},
context_instance=RequestContext(request))
data = file.read()
response = HttpResponse(data, content_type=file.content_type)
response["Content-Disposition"] = "attachment; filename=%s" % id
response["Content-Length"] = len(data)
return response
def get_file_data(self):
"""Returns image file binary data."""
try:
return get_file(self.image_id).read()
except gridfs.errors.NoFile:
raise Exception("Image not found on GridFS storage")
def get_file_data(self):
"""Returns image file binary data."""
try:
return get_file(self.image_id).read()
except gridfs.errors.NoFile:
raise Exception("Image not found on GridFS storage")