Fixed multiple little errors and removed waste code

diaphora.py

@@ -720,7 +720,6 @@ def save_function(self, props):
           except:
             # key doesnt exist because it doesnt have forward references to any bb
             log("Error: %s" % str(sys.exc_info()[1]))
-            pass
 
       # And finally insert the functions to basic blocks relations
       sql = "insert into main.function_bblocks (function_id, basic_block_id) values (?, ?)"
@@ -1196,10 +1195,6 @@ def check_ratio(self, ast1, ast2, pseudo1, pseudo2, asm1, asm2, md1, md2):
       if self.relaxed_ratio or md1 > 10.0:
         return 1.0
       v4 = min((v1 + v2 + v3 + 3.0) / 4, 1.0)
-    elif md1 != 0 and md2 != 0 and False:
-      tmp1 = max(md1, md2)
-      tmp2 = min(md1, md2)
-      v4 = tmp2 * 1. / tmp1
 
     r = max(v1, v2, v3, v4)
     return r
@@ -1576,15 +1571,8 @@ def find_matches_in_hole(self, last, item, row):
                 select * from diff.functions where id = ? """ + postfix
 
       thresold = min(0.6, float(item[5]))
-      done = False
       for j in range(0, min(10, id1 - last)):
-        if done:
-          break
-
         for i in range(0, min(10, id1 - last)):
-          if done:
-            break
-
           cur.execute(sql, (id1+j, id2+i))
           rows = cur.fetchall()
           if len(rows) == 2:
@@ -1713,7 +1701,6 @@ def find_callgraph_matches_from(self, the_items, min_value):
       match = the_items.pop()
       ea1 = match[1]
       name1 = match[2]
-      ea2 = match[3]
       name2 = match[4]
 
       if ea1 in dones:

diaphora_heuristics.py

@@ -1332,7 +1332,6 @@ def check_heuristics_ratio():
 #-------------------------------------------------------------------------------
 def check_mandatory_fields():
   mandatory = set(["name", "ratio", "category", "sql", "flags"])
-  fields = set()
   for heur in HEURISTICS:
     for field in mandatory:
       if field not in heur.keys():

diaphora_ida.py

@@ -1005,7 +1005,7 @@ def import_instruction(self, ins_data1, ins_data2):
         tl.ea = ea1
         tl.itp = mitp
         comment = mcmt
-        ret = cfunc.set_user_cmt(tl, comment)
+        cfunc.set_user_cmt(tl, comment)
         cfunc.save_user_cmts()
 
     tmp_ea = None
@@ -1129,9 +1129,6 @@ def import_instruction_level(self, ea1, ea2, cur):
             address1 = json.loads(diff_rows[0]["assembly_addrs"])
             address2 = json.loads(diff_rows[1]["assembly_addrs"])
 
-            matches = {}
-            to_line = None
-            change_line = None
             diff_list = difflib._mdiff(lines1.splitlines(1), lines2.splitlines(1))
             for x in diff_list:
               left, right, ignore = x
@@ -2413,3 +2410,4 @@ def main():
 
 if __name__ == "__main__":
   main()
+

jkutils/factor.py

@@ -9,7 +9,6 @@
 Copyright (c) 2012-2015 Joxean Koret
 """
 
-import sys
 import random
 import decimal
 

jkutils/graph_hashes.py

@@ -84,10 +84,10 @@ def get_node_value(self, succs, preds):
 
   def get_edges_value(self, bb, succs, preds):
     ret = 1
-    for edge in succs:
+    for _ in succs:
       ret *= EDGE_OUT_CONDITIONAL
 
-    for edge in preds:
+    for _ in preds:
       ret *= EDGE_IN_CONDITIONAL
 
     return ret
@@ -124,8 +124,9 @@ def calculate(self, f):
         if is_call_insn(ea):
           hash *= FEATURE_CALL
 
-        l = DataRefsFrom(ea)
-        hash *= FEATURE_DATA_REFS
+        l = list(DataRefsFrom(ea))
+        if len(l) > 0:
+          hash *= FEATURE_DATA_REFS
 
         for xref in CodeRefsFrom(ea, 0):
           tmp_func = get_func(xref)

jkutils/kfuzzy.py

@@ -38,8 +38,6 @@ def modsum(buf):
     pass
 
 class CFileStr(str):
-    fd = None
-
     def __init__(self, fd):
         self.fd = fd
 
@@ -85,7 +83,6 @@ def edit_distance(self, sign1, sign2):
 
     def simplified(self, bytes, aggresive = False):
         output_size = self.output_size
-        ignore_range = self.ignore_range
         bsize = self.bsize
         total_size = len(bytes)
         size = (total_size/bsize) / output_size
@@ -113,7 +110,6 @@ def _hash(self, bytes, aggresive = False):
         bsize = self.bsize
         total_size = len(bytes)
         rappend = ret.append
-        chunk_size = idx*bsize
         reduce_errors = self.reduce_errors
         # Calculate the sum of every block
         while 1:
@@ -164,7 +160,6 @@ def _fast_hash(self, bytes, aggresive = False):
         ret = set()
 
         output_size = self.output_size
-        size = len(bytes) *1.00 / output_size
         bsize = self.bsize
         radd = ret.add
 
@@ -193,7 +188,6 @@ def _experimental_hash(self, bytes, aggresive = False):
         bsize = self.bsize
         output_size = self.output_size
         size = len(bytes)
-        ignore_range = self.ignore_range
         chunk_size = idx*self.bsize
         byte = None
 
@@ -229,7 +223,6 @@ def mix_blocks(self, bytes):
         ret = ""
         size1 = 0
         size2 = 0
-        total_size = len(bytes)
 
         while 1:
             size1 = idx*self.bsize
@@ -317,6 +310,7 @@ class kfha(kdha):
     the standard python hashlib format. This is the Koret Fast Hashing Algorithm """
 
     def __init__(self, bytes):
+        kdha.__init__(self)
         self._bytes = bytes
         self._kfd = CKoretFuzzyHashing()
         self._kfd.algorithm = self._kfd._fast_hash
@@ -326,6 +320,7 @@ class ksha(kdha):
     the standard python hashlib format. This is the Koret Simplified Hashing Algorithm """
 
     def __init__(self, bytes):
+        kdha.__init__(self)
         self._bytes = bytes
         self._kfd = CKoretFuzzyHashing()
         self._kfd.algorithm = self._kfd.simplified