模块分拆

.idea/Gencoding.iml

@@ -4,7 +4,7 @@
     <content url="file://$MODULE_DIR$">
       <sourceFolder url="file://$MODULE_DIR$/python_lib" isTestSource="false" />
     </content>
-    <orderEntry type="jdk" jdkName="Python 2.7" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="gencoding" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
 </module>

.idea/misc.xml

@@ -1,4 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 2.7" project-jdk-type="Python SDK" />
+  <component name="Black">
+    <option name="sdkName" value="gencoding" />
+  </component>
+  <component name="ProjectRootManager" version="2" project-jdk-name="gencoding" project-jdk-type="Python SDK" />
 </project>

raw-feature-extractor/print_test.py

@@ -21,19 +21,15 @@ import pickle
 # sub_10F20 308  反编译代码有字符串，但是这个特征提取里没有字符串 constant，可能是间接引用的，不识别。看了下所有函数的特征，几乎都没有字符串常量，可能都是写在别的地方然后引用的。
 # sub_166C4 393
 
-
-
-if __name__ == '__main__':
+def main_op(file_path, jsonl_file):
     done_index = 0
-    file_name_list = os.listdir('../A2C/')
-    res_file = "../sample.jsonl"
-    sample_file = open(res_file, mode='a')
+    file_name_list = os.listdir(file_path)
+    sample_file = open(jsonl_file, mode='a')
     for file_name in file_name_list:
         print file_name
-        file_path = '../A2C/' + file_name
-        testpath = '../store/' + file_name + '.ida'
-        if os.path.exists(testpath) and os.path.splitext(file_path)[-1].lower() == '.exe':
-            fr = open(testpath, 'r')
+        file_path_temp = file_path + file_name
+        if os.path.exists(file_path_temp) :
+            fr = open(file_path_temp, 'r')
             data1 = pickle.load(fr)  # 一个二进制文件的acfgs
             # funtion num
             function_number = len(data1.raw_graph_list)
@@ -109,3 +105,8 @@ if __name__ == '__main__':
             print "删除文件" + file_path
             os.remove(file_path)
     sample_file.close()
+
+if __name__ == '__main__':
+    file_path = "../train_malware_result/"
+    jsonl_path = "../jsonl_res/malware_result.jsonl"
+    main_op(file_path, jsonl_path)

raw-feature-extractor/raw_graphs.py

@@ -1,7 +1,7 @@
 import itertools
 import sys
 
-sys.path.insert(1, 'C:/Python27/Lib/site-packages')
+
 import networkx as nx
 # import numpy as np
 from subprocess import Popen, PIPE