fix sleuth error for python3

Makefile.in

@@ -850,7 +850,7 @@ install-data-hook:
 	cp internal.net $(DESTDIR)/$(prefix)/etc/joy
 	mkdir -p $(DESTDIR)/$(prefix)/include/joy
 #	SLEUTHVER= grep version setup.py | awk -F\' '{print $2}'
-	(cd sleuth_pkg && python setup.py bdist --format=gztar)
+	(cd sleuth_pkg && python setup.py bdist --format=gztar && pip install .)
 	tar -xf $(SLEUTHFILE) -C $(DESTDIR)
 
 # Tell versions [3.59,3.63) of GNU make to not export all variables.

sleuth_pkg/sleuth/__init__.py

@@ -1,6 +1,6 @@
 from sleuth import *
-from api_joy import *
-from enrich_tls import enrich_tls
-from fingerprint import *
-from inferences import *
+from sleuth.api_joy import *
+from sleuth.enrich_tls import enrich_tls
+from sleuth.fingerprint import *
+from sleuth.inferences import *
 

sleuth_pkg/sleuth/api_joy.py

@@ -43,6 +43,9 @@
 from .sleuth import DictStreamIteratorFromFile
 from .sleuth import DictStreamIterator
 from .sleuth import SleuthFileType
+from .sleuth import DictStreamProcessor
+from .sleuth import DictStreamFilterIterator
+from .sleuth import SleuthPredicate
 
 
 class FlowIteratorFromFile(DictStreamIteratorFromFile):
@@ -126,8 +129,8 @@ def __init__(self, source):
 
         self.flows = iter(self.active_flows.values())
 
-    def next(self):
-        return self.flows.next()
+    def __next__(self):
+        return self.flows.__next__()
 
     # merge f2 into f1, where both flows are in the same direction, and
     # f1 precedes f2 (f1.ts < f2.ts)
@@ -187,8 +190,8 @@ def __init__(self, source):
     def __iter__(self):
         return self
 
-    def next(self):
-        flow = self.source.next()
+    def __next__(self):
+        flow = self.source.__next__()
         #
         # if flow is not dns, check cache for response returning destination address
         #

sleuth_pkg/sleuth/fingerprint.py

@@ -35,7 +35,7 @@
 """
 import os
 import json
-from sleuth import SleuthTemplateDict
+from .sleuth import SleuthTemplateDict
 
 class fingerprinter(object):
     fingerprint_dict = {

sleuth_pkg/sleuth/inferences.py

@@ -52,11 +52,11 @@ def tls_fp_dict_init():
     with open(tls_fp_path) as f:
         for counter, line in enumerate(f):
             tmp = json.loads(line)
-            #print json.dumps(tmp)
+            #print(json.dumps(tmp))
             fpvalue = json.dumps(tmp['str_repr'])
             fpvalue = fpvalue.strip('"')
             if fpvalue in tls_fp_dict:
-                print "warning: duplicate tls fingerprint in line " + str(counter + 1) + " of file " + tls_fp_file
+                print("warning: duplicate tls fingerprint in line " + str(counter + 1) + " of file " + tls_fp_file)
             tls_fp_dict[fpvalue] = tmp
 
 
@@ -121,30 +121,30 @@ def hex_fp_normalize(s):
 
 def element_is_parent(s):
     if s:
-        if s[0] is '(' and s[1] is '(':
+        if s[0] == '(' and s[1] == '(':
             return True
         else:
             return False
     else:
         return False
 
 def get_next_element(s):
-    if s is '':
+    if s == '':
         return '', '', 0
-    if s[0] is ')':
+    if s[0] == ')':
         level = 0
         for c in s:
-            if c is not ')':
+            if c != ')':
                 break;
             level = level + 1
         return '', '', -level
 
     if True:
         level = 0
-        while s[level] is '(':
+        while s[level] == '(':
             level = level + 1
 
-        if level is 0:
+        if level == 0:
             return '', '', 0
 
         tmp =  string.split(s[level:], ')', 1)
@@ -153,10 +153,10 @@ def get_next_element(s):
 
 def print_out_structured_data(s):
     current_level = 0
-    while s is not '':
+    while s != '':
         element, s, level = get_next_element(s)
         current_level += level
-        print current_level, element, s 
+        print(current_level, element, s)
 
 
 def structured_fp_normalize(s):
@@ -179,7 +179,7 @@ def structured_fp_normalize(s):
 
     # parse client extensions, if present
     output += '('
-    while s is not '' and s is not ')':
+    while s != '' and s != ')':
         element, s, level = get_next_element(s)
         typecode = element[0:4]
         data = element[4:]
@@ -194,7 +194,7 @@ def tls_inference(f, kwargs):
 
     if not tls_fp_dict:
         tls_fp_dict_init()
-        # print json.dumps(tls_fp_dict)
+        # print(json.dumps(tls_fp_dict))
 
     if 'fingerprints' in f:
         if 'tls' in f['fingerprints']:

sleuth_pkg/sleuth/sleuth.py

@@ -55,7 +55,7 @@ def __init__(self):
     def __iter__(self):
         return self
 
-    def next(self):
+    def __next__(self):
         n = dict()
         return n
 
@@ -97,7 +97,7 @@ def _load_file(self):
             else:
                 self.f = open(self.file_name, 'r')
 
-    def next(self):
+    def __next__(self):
         while True:
             try:
                 line = self.f.readline()
@@ -129,15 +129,15 @@ def __init__(self, source, filter):
         self.source = source
         self.filter = filter
 
-    def next(self):
+    def __next__(self):
         """
         Find the next JSON object from source that matches the given filter
         :return:
         """
-        tmp = self.source.next()
+        tmp = self.source.__next__()
 
         while self.filter.match(tmp) is not True:
-            tmp = self.source.next()
+            tmp = self.source.__next__()
 
         return tmp
 
@@ -147,9 +147,9 @@ def __init__(self, source, elements):
         self.source = source
         self.template = SleuthTemplateDict(elements)
 
-    def next(self):
+    def __next__(self):
         while True:
-            tmp = self.source.next()
+            tmp = self.source.__next__()
             output = self.template.copy_selected_elements(self.template.template, tmp)
             if output:
                 return output
@@ -160,8 +160,8 @@ def __init__(self, source, elements):
         self.source = source
         self.template = SleuthTemplateDict(elements)
 
-    def next(self):
-        tmp = self.source.next()
+    def __next__(self):
+        tmp = self.source.__next__()
         output = self.template.normalize_selected_elements(self.template.template, tmp)
 
         return output
@@ -172,8 +172,8 @@ def __init__(self, source, elements, func):
         self.template = SleuthTemplateDict(elements)
         self.func = func
 
-    def next(self):
-        tmp = self.source.next()
+    def __next__(self):
+        tmp = self.source.__next__()
         output = self.template.apply_to_selected_elements(self.template.template, tmp, self.func)
 
         return output
@@ -186,8 +186,8 @@ def __init__(self, source, name, function, **kwargs):
         self.function = function
         self.kwargs = kwargs
 
-    def next(self):
-        nextval = self.source.next()
+    def __next__(self):
+        nextval = self.source.__next__()
         tmp = self.function(nextval, self.kwargs)
         if tmp:
             nextval[self.name] = tmp
@@ -201,8 +201,8 @@ def __init__(self, source, name, function, **kwargs):
         self.function = function
         self.kwargs = kwargs
 
-    def next(self):
-        nextval = self.source.next()
+    def __next__(self):
+        nextval = self.source.__next__()
         tmp = self.function(nextval, self.kwargs)
         if tmp:
             if self.name not in nextval:
@@ -221,9 +221,9 @@ def __init__(self, source, indent=None):
     def __iter__(self):
         return self
 
-    def next(self):
+    def __next__(self):
         try:
-            obj = self.source.next()
+            obj = self.source.__next__()
             value = pickle.dumps(obj)
             self.key = tuple(obj.keys())
             if value in self.dist:
@@ -244,7 +244,7 @@ def next(self):
 
             for d in output:
                 json.dump(d, sys.stdout, indent=self.indent)
-                print ""
+                print("")
 
             raise StopIteration
 
@@ -277,7 +277,7 @@ def post_process(self, proc=None):
             for obj in self.obj_set:
                 try:
                     json.dump(obj, sys.stdout, indent=self.indent)
-                    print ""
+                    print("")
                 except IOError:
                     # Broken pipe, exit loop
                     break
@@ -301,7 +301,7 @@ def main_process(self, obj):
 
     def post_process(self, proc=None):
         if self.context:
-            print self.context
+            print(self.context)
 
         for k, v in self.dict.items():
             v.post_process(copy.deepcopy(proc))
@@ -348,7 +348,7 @@ def post_process(self):
         # NOTE: sum_over might interfere with --dist
         d["sum_over"] = self.total
         json.dump(d, sys.stdout, indent=self.indent)
-        print ""
+        print("")
 
 
 class DictStreamDistributionProcessor(DictStreamProcessor):
@@ -379,7 +379,7 @@ def post_process(self):
 
         for d in output:
             json.dump(d, sys.stdout, indent=self.indent)
-            print ""
+            print("")
 
 
 """
@@ -413,7 +413,7 @@ def string_to_template_object(self, s):
         if needArg:
             t += "None"
         t += '}'
-        #print "t: " + t
+        #print("t: " + t)
         return eval(t)
 
     def copy_selected_elements(self, tmplDict, obj):
@@ -543,9 +543,9 @@ def __init__(self, elements):
             self.matchAll = True
 
     def eval(self, flow):
-        # print 'flow: ' + str(flow)
-        # print 'op: ' + str(self.op)
-        # print 'arg: ' + str(self.arg)
+        # print('flow: ' + str(flow))
+        # print('op: ' + str(self.op))
+        # print('arg: ' + str(self.arg))
 
         # If flow is list, match any element in it
         if isinstance(flow, list):
@@ -561,8 +561,9 @@ def eval(self, flow):
                             listMatch = True
             return listMatch
         elif isinstance(flow, dict):
-            # print 'dict flow: ' + str(flow)
-            x = flow.values()[0]
+            # print('dict flow: ' + str(flow))
+
+            x = list(flow.values())[0]
             return self.eval(x)
 
         if self.op == '=':
@@ -571,9 +572,9 @@ def eval(self, flow):
             elif isinstance(self.arg, int):
                 return self.arg == flow
             else:
-                # print '------------------'
-                # print 'flow: ' + str(flow)
-                # print 'arg:  ' + str(self.arg)
+                # print('------------------')
+                # print('flow: ' + str(flow))
+                # print('arg:  ' + str(self.arg)
                 return fnmatch.fnmatch(flow, self.arg)
         elif self.op == '~':
             if self.arg == '*':
@@ -593,7 +594,7 @@ def match(self, flow):
         else:
             output = self.template.get_selected_element(self.template.template, flow)
             if output:
-                return self.eval(output.values()[0])
+                return self.eval(list(output.values())[0])
             else:
                 if self.op == '~' and self.arg == '*':
                     # True because element is absent from flow