added support for proper unicode session(s) storage/retrieval

stamparm · stamparm · commit e9be60e1ac94 · 2010-05-24T11:00:49.000Z
diff --git a/lib/core/common.py b/lib/core/common.py
@@ -22,6 +22,7 @@
 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 """
 
+import codecs
 import cProfile
 import os
 import random
@@ -351,8 +352,11 @@ def filePathToString(filePath):
     return strRepl
 
 def dataToStdout(data):
-    sys.stdout.write(data)
-    sys.stdout.flush()
+    try:
+        sys.stdout.write(data)
+        sys.stdout.flush()
+    except UnicodeEncodeError:
+        print data.encode("utf8")
 
 def dataToSessionFile(data):
     if not conf.sessionFile:
@@ -371,7 +375,7 @@ def dataToOutFile(data):
 
     rFile     = filePathToString(conf.rFile)
     rFilePath = "%s%s%s" % (conf.filePath, os.sep, rFile)
-    rFileFP   = open(rFilePath, "wb")
+    rFileFP   = codecs.open(rFilePath, "wb", "utf-8")
 
     rFileFP.write(data)
     rFileFP.flush()
@@ -412,7 +416,7 @@ def fileToStr(fileName):
     @rtype: C{str}
     """
 
-    filePointer = open(fileName, "r")
+    filePointer = codecs.open(fileName, "r", "utf-8")
     fileText = filePointer.read()
 
     return fileText.replace("    ", "").replace("\t", "").replace("\r", "").replace("\n", " ")
diff --git a/lib/core/dump.py b/lib/core/dump.py
@@ -22,8 +22,9 @@
 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 """
 
-import os
+import codecs
 import re
+import os
 
 from lib.core.common import dataToDumpFile
 from lib.core.data import conf
@@ -54,7 +55,7 @@ def __write(self, data, n=True):
         
     def setOutputFile(self):
         self.__outputFile = "%s%slog" % (conf.outputPath, os.sep)
-        self.__outputFP = open(self.__outputFile, "a")
+        self.__outputFP = codecs.open(self.__outputFile, "a", "utf-8")
         
     def string(self, header, data, sort=True):
         if isinstance(data, (list, tuple, set)):
@@ -267,7 +268,7 @@ def dbTableValues(self, tableValues):
                 os.makedirs(dumpDbPath, 0755)
 
             dumpFileName = "%s%s%s.csv" % (dumpDbPath, os.sep, table)
-            dumpFP = open(dumpFileName, "w")
+            dumpFP = codecs.open(dumpFileName, "w", "utf-8")
 
         count     = int(tableValues["__infos__"]["count"])
         separator = ""
@@ -319,13 +320,14 @@ def dbTableValues(self, tableValues):
             for column in columns:
                 if column != "__infos__":
                     info = tableValues[column]
-                    value = info["values"][i]
 
-                    if re.search("^[\ *]*$", str(value)):
+                    value = unicode(info["values"][i]) if type(info["values"][i]) != unicode else info["values"][i]
+
+                    if re.search("^[\ *]*$", value):
                         value = "NULL"
 
                     maxlength = int(info["length"])
-                    blank = " " * (maxlength - len(str(value)))
+                    blank = " " * (maxlength - len(value))
                     self.__write("| %s%s" % (value, blank), n=False)
 
                     if not conf.multipleTargets and field == fields:
diff --git a/lib/core/option.py b/lib/core/option.py
@@ -22,6 +22,7 @@
 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 """
 
+import codecs
 import cookielib
 import ctypes
 import difflib
@@ -96,7 +97,7 @@ def __urllib2Opener():
     urllib2.install_opener(opener)
 
 def __feedTargetsDict(reqFile, addedTargetUrls):
-    fp = open(reqFile, "r")
+    fp = codecs.open(reqFile, "r", "utf-8")
 
     fread = fp.read()
     fread = fread.replace("\r", "")
diff --git a/lib/core/target.py b/lib/core/target.py
@@ -22,6 +22,7 @@
 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 """
 
+import codecs
 import os
 import time
 
@@ -121,11 +122,11 @@ def __setOutputResume():
 
     if os.path.exists(conf.sessionFile):
         if not conf.flushSession:
-            readSessionFP = open(conf.sessionFile, "r")
+            readSessionFP = codecs.open(conf.sessionFile, "r", "utf-8")
             __url_cache = set()
             __expression_cache = {}
 
-            for line in readSessionFP.xreadlines():
+            for line in readSessionFP.readlines(): #xreadlines doesn't return unicode strings when codec.open used
                 if line.count("][") == 4:
                     line = line.split("][")
 
@@ -170,7 +171,7 @@ def __setOutputResume():
                 raise sqlmapFilePathException, errMsg
 
     try:
-        conf.sessionFP = open(conf.sessionFile, "a")
+        conf.sessionFP = codecs.open(conf.sessionFile, "a", "utf-8")
         dataToSessionFile("\n[%s]\n" % time.strftime("%X %x"))
     except IOError:
         errMsg = "unable to write on the session file specified"
diff --git a/lib/techniques/blind/inference.py b/lib/techniques/blind/inference.py
@@ -194,10 +194,10 @@ def getChar(idx, charTbl=asciiTbl):
                     minValue = charTbl[0]
                 else:
                     retVal = minValue + 1
-                    if retVal < 256:
+                    if retVal < 128:
                         return chr(retVal)
                     else:
-                        return unichr(retVal)
+                        return unichr(retVal) #test value 50089
 
     def etaProgressUpdate(charTime, index):
         if len(progressTime) <= ( (length * 3) / 100 ):
