Merge pull request #104 from akisari/master

Fix the text parser used for tests.

tests/core/core.py

@@ -150,7 +150,10 @@ class Core(object):
         ldiff = list()
         diffobj = diff.Diff()
         for it in range(0, len(outresult)):
-            ldiff.append(diffobj.diffobj(outresult[it], outtest[it]))
+            td = diffobj.diffobj(outresult[it], outtest[it])
+            ldiff.append(td[:])
+            td = diffobj.diffobj(outtest[it], outresult[it])
+            ldiff.append(td[:])
 
         result = result.replace("\r", "")
         subprocess = subresult.replace("\r", "")

tests/core/diff.py

@@ -25,7 +25,8 @@ class Diff(object):
                     ]
                     self._diff.append(result)
             else:
-                result = [" - KEY %s : " % (key), " + KEY %s : " % (key)]
+                result = [" - KEY %s : %s" % (key, dict1[key]), " + KEY %s : " % (key)]
+                self._diff.append(result)
 
     def diffobj(self, actual: object, expected: object) -> list:
         """
@@ -33,11 +34,11 @@ class Diff(object):
         """
         self._diff.clear()
         if len(actual) != len(expected):
-            self._diff.append("invalid dimensions")
-            return None
-
-        for it in range(0, len(actual)):
-            self.diff(actual[it]._data, expected[it]._data)
+            result = [" - ACTUAL DIM = %d" % (len(actual)), "+ EXPECTED DIM = %d" % (len(expected))]
+            self._diff.append(result)
+        else:
+            for it in range(0, len(actual)):
+                self.diff(actual[it]._data, expected[it]._data)
 
         if self._diff:
             for elem in self._diff:

tests/core/objects.py

@@ -105,31 +105,58 @@ class ShemuInstrux(DecodeShemuParser):
         """
         Parses the emulation result generated by disasmtool and stores it in a dictionary as key:value pair as follows:
         {
-            "AX": "0x0000000000000000",
-            "CX": "0x0000000000000000",
-            "DX": "0x0000000000000000",
-            "BX": "0x0000000000000000",
-            "BP": "0x0000000000000000",
-            "SI": "0x0000000000000000",
+            "RAX": "0x0000000000000000",
+            "RCX": "0x0000000000000000",
+            "RDX": "0x0000000000000000",
+            "RBX": "0x0000000000000000",
+            "RBP": "0x0000000000000000",
+            "RSI": "0x0000000000000000",
             ...
-            "28": "0x0000000000000000",
-            "29": "0x0000000000000000",
-            "30": "0x0000000000000000",
-            "31": "0x0000000000000000",
-            "IP": "0x0000000000200000",
-            "GS": "0x0000000000000202"
+            "R28": "0x0000000000000000",
+            "R29": "0x0000000000000000",
+            "R30": "0x0000000000000000",
+            "R31": "0x0000000000000000",
+            "RIP": "0x0000000000200000",
+            "RFLAGS": "0x0000000000000202"
         }
         """
         self._obj = self._obj.split("\n")
         line = self.rdline()
+        cnt = 0
         while line:
-            # X0  = 0x0000000000000000 X1  = 0x0000000000000000 X2  = 0x0000000000000000 X3  = 0x0000000000000000
             if " = " in line:
-                tokens = re.findall(r"\w\w\s*=\s*0x\d{16}", line)
+                tokens = re.findall(r"\w+\s*=\s*[0x]*[\da-f]{4,16}", line)
                 for token in tokens:
                     key = token.lstrip().rstrip().split("=")[0].lstrip().rstrip()
                     val = token.lstrip().rstrip().split("=")[1].lstrip().rstrip()
                     self._data[key] = val
+            if "IP: " in line or "PC: " in line:
+                tokens = re.findall(r"\w\w\s*:\s*0x[\da-f]{16}", line)
+                key = tokens[0].lstrip().rstrip().split(":")[0].lstrip().rstrip()
+                val = tokens[0].lstrip().rstrip().split(":")[1].lstrip().rstrip()
+                self._data["%s-%s" % (key, "INFO")] = val
+
+                tokens = line.split('  ')
+                key = "InstructionBytes"
+                val = tokens[1].lstrip().rstrip()
+                self._data[key] = val
+
+                key = "InstructionText"
+                val = " ".join(tokens[2:]).lstrip().rstrip()
+                self._data[key] = val
+            elif "Detection: " in line:
+                tokens = re.findall(r"\w+\s*:\s*0x\d{16}", line)
+                key = tokens[0].lstrip().rstrip().split(":")[0].lstrip().rstrip()
+                val = tokens[0].lstrip().rstrip().split(":")[1].lstrip().rstrip()
+                self._data["%s-%d" % (key, cnt)] = val
+                cnt += 1
+            elif ":" in line:
+                tokens = re.findall(r"\w\w\s*:\s*\d{1}", line)
+                for token in tokens:
+                    key = token.lstrip().rstrip().split(":")[0].lstrip().rstrip()
+                    val = token.lstrip().rstrip().split(":")[1].lstrip().rstrip()
+                    self._data[key] = val
+
             line = self.rdline()
 
 

tests/core/output.py

@@ -100,7 +100,7 @@ class OutputShemu(OutputParser):
         for line in data.split("\n"):
             if line.startswith("Emulation ") or "SHEMU" in line:
                 continue
-            if re.search("^PC:", line) or re.search("^IP:", line):
+            if re.search(r"^\s*\wAX =", line) or re.search("^\s*X0\s*= ", line):
                 if local:
                     local = local.replace("\r", "")
                     ostr.append(local)