added vd + fixes

setup.py

@@ -12,7 +12,7 @@
     url='http://vdiscover.org/',
     author='G.Grieco',
     author_email='[email protected]',
-    scripts=['fextractor', 'vpredictor', 'tcreator', 'vdp'],
+    scripts=['fextractor', 'vpredictor', 'tcreator', 'vd'],
     install_requires=[
         "python-ptrace",
         "scikit-learn"

vd

@@ -0,0 +1,67 @@
+#!/usr/bin/python2
+
+"""
+This file is part of VDISCOVER.
+
+VDISCOVER is free software: you can redistribute it and/or modify
+it under the terms of the GNU General Public License as published by
+the Free Software Foundation, either version 3 of the License, or
+(at your option) any later version.
+
+VDISCOVER is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+GNU General Public License for more details.
+
+You should have received a copy of the GNU General Public License
+along with VDISCOVER. If not, see <http://www.gnu.org/licenses/>.
+
+Copyright 2014 by G.Grieco
+"""
+
+import os
+import argparse
+import sys
+import csv
+
+#from vdiscover.Detection import WriteTestcase
+from vdiscover.Process    import Process
+from vdiscover.Printer    import TypePrinter
+from vdiscover.Cluster  import Cluster
+
+if __name__ == "__main__":
+
+    # Arguments
+    parser = argparse.ArgumentParser(description='')
+    parser.add_argument("seeds", help="", type=str, default=None)
+    parser.add_argument("vectorizer", help="", type=str, default=None)
+    parser.add_argument("cmd", help="", type=str, default=None)
+
+    options = parser.parse_args()
+    seeds = options.seeds
+    cmd = options.cmd
+    vectorizer = options.vectorizer
+    #outdir = "outdir/"++
+    program = cmd.split(" ")[0]
+    timeout = 5
+    envs = dict()
+
+    app = Process(program, envs, timeout, [], [], True)
+    prt = TypePrinter("/dev/null", program, 0)
+    traces = []
+
+    print "Extracting traces.."
+    for x,y,files in os.walk(seeds):
+      for f in files:
+        prepared_cmd = cmd.replace(program,"")
+        prepared_cmd = prepared_cmd.split("@@")
+        prepared_cmd = prepared_cmd[0].split(" ") + [x+"/".join(y)+"/"+f] + prepared_cmd[1].split(" ")
+        prepared_cmd = filter(lambda x: x<>'', prepared_cmd)
+        events = app.getData(prepared_cmd)
+        traces.append(prt.print_events(events))
+        #print prepared_cmd
+        #print traces[-1]
+
+    Cluster(vectorizer, None, traces, None, "cluster", "dynamic", None)
+
+

vdiscover/Printer.py

@@ -100,3 +100,4 @@ def print_events(self, events):
 
     self.csvwriter.writerow(row)
     self.outfile.flush()
+    return row

vdiscover/Utils.py

@@ -77,7 +77,13 @@ def open_model(model_file):
 
 def read_traces(train_file, nsamples, cut=None, maxsize=50):
 
-  csvreader = load_csv(train_file)
+  if type(train_file) == str:
+    csvreader = load_csv(train_file)
+  elif type(train_file) == list:
+    csvreader = train_file
+  else:
+    assert(0)
+
   train_features = []
   train_programs = []
   train_classes = []
@@ -121,7 +127,12 @@ def read_traces(train_file, nsamples, cut=None, maxsize=50):
           train_classes.append(cl)
   else:
 
-    train_size = file_len(train_file)
+    if type(train_file) == str:
+      train_size = file_len(train_file)
+    elif type(train_file) == list:
+      train_size = len(csvreader)
+
+    #train_size = file_len(train_file)
     skip_until = random.randint(0,train_size - nsamples)
 
     for i,col in enumerate(csvreader):