Added few comments

bin/Duplicate_ssdeep_v2.py

@@ -11,6 +11,8 @@ Its input comes from other modules, namely:
 
 This one differ from v1 by only using redis and not json file stored on disk
 
+Perform comparisions with ssdeep and tlsh
+
 Requirements:
 -------------
 
@@ -130,18 +132,17 @@ if __name__ == "__main__":
                                 print '['+hash_type+'] '+'comparing: ' + str(PST.p_path[44:]) + '  and  ' + str(paste_path[44:]) + ' percentage: ' + str(percent)
                         except Exception,e:
                             print str(e)
-                            # ssdeep hash not comparable
                             #print 'hash not comparable, bad hash: '+dico_hash+' , current_hash: '+paste_hash
-                            #curr_dico_redis.srem('HASHS', dico_hash)
 
             # Add paste in DB after checking to prevent its analysis twice
-            # hash_i -> index_i  AND  index_i -> PST.PATH
+            # hash_type_i -> index_i  AND  index_i -> PST.PATH
             r_serv1.set(index, PST.p_path)
             r_serv1.sadd("INDEX", index)
-            # Adding the hash in Redis
+            # Adding hashes in Redis
             for hash_type, paste_hash in paste_hashes.iteritems():
                 r_serv1.set(paste_hash, index)
                 r_serv1.sadd("HASHS_"+hash_type, paste_hash)
+
     ##################### Similarity found  #######################
 
             # if there is data in this dictionnary

bin/packages/Paste.py

@@ -165,7 +165,7 @@ class Paste(object):
         """
         Setting the hash of the paste as a kind of "uniq" identificator
 
-        :return: hash string (md5, sha1....)
+        :return: a dictionnary of hash string (md5, sha1....)
 
         :Example: PST._get_p_hash()
 

var/www/Flask_server.py

@@ -14,7 +14,7 @@ import Paste
 from Date import Date
 
 # CONFIG #
-tlsh_to_percent = 1000.0
+tlsh_to_percent = 1000.0 #Use to display the estimated percentage instead of a raw value
 
 configfile = os.path.join(os.environ['AIL_BIN'], 'packages/config.cfg')
 if not os.path.exists(configfile):
@@ -124,6 +124,7 @@ def showpaste(content_range):
             
     p_duplicate_full_list.sort(lambda x,y: cmp(x[2], y[2]), reverse=True)
 
+    # Combine multiple duplicate paste name and format for display
     new_dup_list = []
     dup_list_removed = []
     for dup_list_index in range(0, len(p_duplicate_full_list)):
@@ -141,6 +142,7 @@ def showpaste(content_range):
         comp_vals = str(comp_vals).replace("[","").replace("]","") if len(comp_vals)==1 else str(comp_vals)
         new_dup_list.append([hash_types.replace("'", ""), p_duplicate_full_list[dup_list_index][1], comp_vals])
 
+    # Create the list to pass to the webpage
     for dup_list in new_dup_list:
         hash_type, path, simil_percent = dup_list
         p_duplicate_list.append(path)