In [1]:

    

%load_ext autoreload
import re
%aimport asm_utils


    

In [2]:

    

samples = asm_utils.get_collection()


    

In [3]:

    

# get names of files from mongo; testing with class 5
names = [post['id'] for post in samples.find({'class':'5'})]
test_file = names[0]
test_file


    

    
Out[3]:





'1IpWLz6eyhVxDAfQMKEd'

In [4]:

    

test_id = '0qjuDC7Rhx9rHkLlItAp'
post_test = samples.find_one({'id': test_id})
print(post_test['id'])


    

    




0qjuDC7Rhx9rHkLlItAp

In [5]:

    

with open('asm_instructions.csv', 'r') as f:
    asm_instr = [line.strip() for line in f.readlines()]


    

In [104]:

    

asm = asm_utils.read_assembly(post['id'])
instr_seq = asm_utils.get_inst(asm, asm_instr)
test_asm_info = asm_seq_info(instr_seq)


    

In [51]:

    

# test_a = [to_utf(a) for a in asm if len(a) > 1]
# words = [line.split() for line in test_a if line != None]


    

In [6]:

    

def make_asm_info(post):
    """Takes a mongodb post and inserts information about it's assembly code in it"""
    asm = asm_utils.read_assembly(post['id'])
    instr_seq = asm_utils.get_inst(asm, asm_instr)
    post['asm_info'] = asm_utils.asm_seq_info(instr_seq)
    #post['asm_instr_seq'] = instr_seq
    #post['asm_instr_count'] = len(instr_seq)
    #post['asm_uniq_instr'] = set(instr_seq)
    #post['asm_uniq_count'] = len(set(instr_seq))
    samples.save(post)


    

In [7]:

    




    

In [8]:

    

make_asm_info(post_test)


    

In [13]:

    

documents = samples.find()


    

In [15]:

    

for doc in documents:
    print('extracting assembly info for %s' % doc['id'])
    make_asm_info(doc)


    

    
Out[15]:





10868

In [10]:

    




    

In [21]:

    




    

In [66]:

    




    

In [34]:

    




    

In [117]:

    




    

In [118]:

    

jumps = [word for word in a if word  in ['je', 'ne', 'jz', 'jg', 'jge', 'jl', 'jle']]


    

In [113]:

    




    

In [114]:

    

# lcss


    

    
Out[114]:





34

In [117]:

    




    

    
Out[117]:





ObjectId('5513a805127d27664d47bd44')

In [130]:

    

def update_collection(collection, _id, key, value):
    # samples.update({'id': test_file}, {"$set": {'ida_comments': test_comments }})
    if id is None:
        print('you must pass an id')
        return
    print(collection)
    # print('updating %s with %s' % (_id, value['num_instr']))
    collection.update({'id': _id},
                      {"$set": {key :  value }})


    

In [12]:

    




    

In [8]:

    




    

In [131]:

    

update_collection(samples, test_file, 'asm_count', 'x')


    

    




Collection(Database(MongoClient('afruizc-office.cs.unm.edu', 27017), 'malware'), 'samples')

In [60]:

    




    

    




<class 'str'>

In [118]:

    




    

In [9]:

    

a = samples.find({'id': post_test['id']})


    

In [12]:

    

a[0]['asm_info']['num_instr']


    

    
Out[12]:





2348

In [ ]:

    




    

In [ ]: