From 565f61a6abc30dfb4df0269384466589690fbae5 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Fri, 2 Apr 2021 20:09:16 +0400
Subject: [PATCH 01/25] Initialalize the autodict-ql

Initialalize the autodict-ql
add codeql scripts
---
 utils/autodict_ql/litool.ql      | 10 ++++++++++
 utils/autodict_ql/memcmp-str.ql  |  8 ++++++++
 utils/autodict_ql/strcmp-str.ql  |  8 ++++++++
 utils/autodict_ql/strncmp-str.ql |  8 ++++++++
 utils/autodict_ql/strtool.ql     | 24 ++++++++++++++++++++++++
 5 files changed, 58 insertions(+)
 create mode 100644 utils/autodict_ql/litool.ql
 create mode 100644 utils/autodict_ql/memcmp-str.ql
 create mode 100644 utils/autodict_ql/strcmp-str.ql
 create mode 100644 utils/autodict_ql/strncmp-str.ql
 create mode 100644 utils/autodict_ql/strtool.ql

diff --git a/utils/autodict_ql/litool.ql b/utils/autodict_ql/litool.ql
new file mode 100644
index 00000000..b7f4bf33
--- /dev/null
+++ b/utils/autodict_ql/litool.ql
@@ -0,0 +1,10 @@
+import cpp
+
+class HexOrOctLiteral extends Literal{
+    HexOrOctLiteral(){
+      (this instanceof HexLiteral) or (this instanceof OctalLiteral)
+    }
+}
+
+from HexOrOctLiteral lit
+select lit.getValueText()
\ No newline at end of file
diff --git a/utils/autodict_ql/memcmp-str.ql b/utils/autodict_ql/memcmp-str.ql
new file mode 100644
index 00000000..830c9cac
--- /dev/null
+++ b/utils/autodict_ql/memcmp-str.ql
@@ -0,0 +1,8 @@
+import cpp 
+
+/// function :  memcmp trace
+
+from FunctionCall fucall, Expr size
+where
+    fucall.getTarget().hasName("memcmp")
+select fucall.getArgument(_).getValueText()	
\ No newline at end of file
diff --git a/utils/autodict_ql/strcmp-str.ql b/utils/autodict_ql/strcmp-str.ql
new file mode 100644
index 00000000..83ffadaf
--- /dev/null
+++ b/utils/autodict_ql/strcmp-str.ql
@@ -0,0 +1,8 @@
+import cpp 
+
+/// function : strcmp
+
+from FunctionCall fucall, Expr size
+where
+    fucall.getTarget().hasName("strcmp")
+select fucall.getArgument(_).getValueText()
\ No newline at end of file
diff --git a/utils/autodict_ql/strncmp-str.ql b/utils/autodict_ql/strncmp-str.ql
new file mode 100644
index 00000000..dbb952e5
--- /dev/null
+++ b/utils/autodict_ql/strncmp-str.ql
@@ -0,0 +1,8 @@
+import cpp 
+
+/// function : strncmp
+
+from FunctionCall fucall, Expr size
+where
+    fucall.getTarget().hasName("strncmp")
+select fucall.getArgument(_).getValueText()
\ No newline at end of file
diff --git a/utils/autodict_ql/strtool.ql b/utils/autodict_ql/strtool.ql
new file mode 100644
index 00000000..f78aabbb
--- /dev/null
+++ b/utils/autodict_ql/strtool.ql
@@ -0,0 +1,24 @@
+import cpp
+import semmle.code.cpp.dataflow.DataFlow
+class StringLiteralNode extends DataFlow::Node {
+  StringLiteralNode() { this.asExpr() instanceof StringLiteral }
+}
+class MemcmpArgNode extends DataFlow::Node {
+   MemcmpArgNode() {
+    exists(FunctionCall fc |
+      fc.getTarget().getName().regexpMatch(".*(str|mem|strn|b)*(cmp|str)*") and
+      fc.getArgument(0) = this.asExpr() 
+    )
+ or
+    exists(FunctionCall fc |
+      fc.getTarget().getName().regexpMatch(".*(str|mem|strn|b)*(cmp|str)*") and
+      fc.getArgument(1) = this.asExpr()
+    )
+  }
+}
+
+from StringLiteralNode src, MemcmpArgNode arg
+where
+  DataFlow::localFlow(src, arg)
+
+select src.asExpr().(StringLiteral).toString()
\ No newline at end of file

From a26ed3b7580e31b6f6f174169528fc0bebe20ad6 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 02:02:45 +0400
Subject: [PATCH 02/25] update the codes, readme

- add readme
- add required qlpack.yml
---
 utils/autodict_ql/autodict_ql.py  | 188 ++++++++++++++++++++++++++++++
 utils/autodict_ql/build-codeql.sh |  17 +++
 utils/autodict_ql/litan.py        |  86 ++++++++++++++
 utils/autodict_ql/qlpack.yml      |   3 +
 utils/autodict_ql/readme.md       |  81 +++++++++++++
 utils/autodict_ql/strtool.ql      |   6 +-
 6 files changed, 378 insertions(+), 3 deletions(-)
 create mode 100644 utils/autodict_ql/autodict_ql.py
 create mode 100644 utils/autodict_ql/build-codeql.sh
 create mode 100644 utils/autodict_ql/litan.py
 create mode 100644 utils/autodict_ql/qlpack.yml
 create mode 100644 utils/autodict_ql/readme.md

diff --git a/utils/autodict_ql/autodict_ql.py b/utils/autodict_ql/autodict_ql.py
new file mode 100644
index 00000000..69d11f48
--- /dev/null
+++ b/utils/autodict_ql/autodict_ql.py
@@ -0,0 +1,188 @@
+#!/usr/bin/env python3
+import os
+import string
+import binascii 
+import codecs
+import errno
+import struct
+import argparse
+import shutil
+import subprocess
+
+from binascii import unhexlify
+
+def ensure_dir(dir):
+    try:
+        os.makedirs(dir)
+    except OSError as e:
+        if e.errno != errno.EEXIST:
+            raise
+
+def parse_args():
+    parser = argparse.ArgumentParser(description=(
+        "Helper - Specify input file analysis and output folder to save corpus for strings in the overall project ---------------------------------------------------------------------------  Example usage : python2 thisfile.py outdir str.txt"    ))
+    
+    #parser.add_argument("tokenpath",
+        #help="Destination directory for tokens")
+    parser.add_argument("cur",
+            help = "Current Path")
+    parser.add_argument("db",
+            help = "CodeQL database Path")
+    parser.add_argument("tokenpath",
+            help="Destination directory for tokens")
+
+    return parser.parse_args()
+
+def static_analysis(file,file2,cur,db) :
+    with open(cur+"/"+file, "w") as f:
+        print(cur+"/"+file)
+        stream = os.popen("codeql query run " + cur +"/"+ file2 +  " -d " + db )
+        output = stream.read()
+        f.write(output)
+        f.close()
+
+def copy_tokens(cur, tokenpath) :
+    subprocess.call(["cp " + cur  + "/" + "arrays-lits/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["cp " + cur  + "/" + "strstr-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["cp " + cur  + "/" + "strcmp-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["cp " + cur  + "/" + "strncmp-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["cp " + cur  + "/" + "local-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["cp " + cur  + "/" + "memcmp-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["cp " + cur  + "/" + "global-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["cp " + cur  + "/" + "lits/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["cp " + cur  + "/" + "arrays-lits/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["cp " + cur  + "/" + "arrays-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["cp " + cur  + "/" + "strtool-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    #strtool-strs
+
+
+def codeql_analysis(cur, db) :
+    static_analysis("litout.out","litool.ql", cur, db)
+    static_analysis("strcmp-strings.out","strcmp-str.ql", cur, db)
+    static_analysis("strncmp-strings.out","strncmp-str.ql", cur, db)
+    static_analysis("strstr-strings.out","strstr-str.ql", cur, db)
+    static_analysis("memcmp-strings.out","memcmp-str.ql", cur, db)
+    static_analysis("global-values-strings.out","globals-values.ql", cur, db)
+    static_analysis("local-strings.out","locals-strs.ql", cur, db)
+    static_analysis("strtool-strings.out","strtool.ql", cur, db)
+    static_analysis("arrays.out","array-literals.ql", cur, db)
+    start_aflql(0,cur)
+    #command1 = [
+    #       'codeql','query', 'run',
+    #       cur + '/litool.ql',
+    #       '-d',
+    #       db, '>','fff.txt'
+    #    ]
+    #with open("litool2.log", "w") as f:
+    #    stream = os.popen("codeql query run litool.ql -d " + db )
+    #    output = stream.read()
+    #    f.write(output)
+    #    f.close()
+    #worker1 = subprocess.Popen(command1)
+    #print(worker1.communicate())
+
+
+def start_aflql(tokenpath, cur):
+    command = [
+           'python3',
+           cur + '/litan.py',
+           cur+'/lits/',
+           cur+'/litout.out'
+        ]
+    worker1 = subprocess.Popen(command)
+    print(worker1.communicate())
+    
+    command1 = [
+           'python3',
+           cur + '/strcmp-strings.py',
+           cur + '/strcmp-strs/',
+           cur + '/strcmp-strings.out'
+        ]
+    worker2 = subprocess.Popen(command1)
+    print(worker2.communicate())
+
+    command2 = [
+           'python3',
+           cur + '/strncmp-strings.py',
+           cur + '/strncmp-strs/',
+           cur + '/strncmp-strings.out'
+        ]
+    worker3 = subprocess.Popen(command2)
+    print(worker3.communicate())
+
+    command3 = [
+           'python3',
+           cur + '/array-lits.py',
+           cur + '/arrays-lits/',
+           cur + '/arrays.out'
+        ]
+    worker4 = subprocess.Popen(command3)
+    print(worker4.communicate())
+
+    command4 = [
+           'python3',
+           cur + '/array-strings.py',
+           cur + '/arrays-strs/',
+           cur + '/arrays.out'
+        ]
+    worker5 = subprocess.Popen(command4)
+    print(worker5.communicate())
+
+
+    command5 = [
+           'python3',
+           cur + '/memcmp-strings.py',
+           cur + '/memcmp-strs/',
+           cur + '/memcmp-strings.out'
+        ]
+    worker6 = subprocess.Popen(command5)
+    print(worker6.communicate())
+
+    command6 = [
+           'python3',
+           cur + '/globals-strings.py',
+           cur + '/global-strs/',
+           cur + '/global-values-strings.out'
+        ]
+    worker7 = subprocess.Popen(command6)
+    print(worker7.communicate())
+
+    command7 = [
+           'python3',
+           cur + '/strstr-strings.py',
+           cur + '/strstr-strs/',
+           cur + '/strstr-strings.out'
+        ]
+    worker8 = subprocess.Popen(command7)
+    print(worker8.communicate())
+
+
+    #strtool-strings.out
+
+    command8 = [
+           'python3',
+           cur + '/stan-strings.py',
+           cur + '/strtool-strs/',
+           cur + '/strtool-strings.out'
+        ]
+    worker9 = subprocess.Popen(command8)
+    print(worker9.communicate())
+
+    command9 = [
+           'python3',
+           cur + '/local-strings.py',
+           cur + '/local-strs/',
+           cur + '/local-strings.out'
+        ]
+    worker10 = subprocess.Popen(command9)
+    print(worker10.communicate())
+
+def main():
+    args = parse_args()    
+    ensure_dir(args.tokenpath)
+    #copy_tokens(args.cur, args.tokenpath)
+    codeql_analysis(args.cur, args.db)
+    copy_tokens(args.cur, args.tokenpath)
+    #start_aflql(args.tokenpath, args.cur)
+if __name__ == '__main__':
+    main()
\ No newline at end of file
diff --git a/utils/autodict_ql/build-codeql.sh b/utils/autodict_ql/build-codeql.sh
new file mode 100644
index 00000000..ccff932e
--- /dev/null
+++ b/utils/autodict_ql/build-codeql.sh
@@ -0,0 +1,17 @@
+cd ~
+if [ -d "codeql-home" ]; then
+    echo "Exist !"
+    exit 1
+fi
+sudo apt install build-essential libtool-bin python3-dev automake git vim wget -y
+mkdir codeql-home
+cd codeql-home
+git clone https://github.com/github/codeql.git codeql-repo
+git clone https://github.com/github/codeql-go.git
+wget https://github.com/github/codeql-cli-binaries/releases/download/v2.4.6/codeql-linux64.zip
+unzip codeql-linux64.zip 
+mv codeql codeql-cli
+export "PATH=~/codeql-home/codeql-cli/:$PATH"
+codeql resolve languages
+codeql resolve qlpacks
+echo "export PATH=~/codeql-home/codeql-cli/:$PATH" >> ~/.bashrc
\ No newline at end of file
diff --git a/utils/autodict_ql/litan.py b/utils/autodict_ql/litan.py
new file mode 100644
index 00000000..18c04c34
--- /dev/null
+++ b/utils/autodict_ql/litan.py
@@ -0,0 +1,86 @@
+#!/usr/bin/env python3
+# Autodict-QL - Optimal token generation for fuzzing
+# Part of AFL++ Project
+# Author : Microsvuln - Arash.vre@gmail.com
+import string
+import os
+import binascii 
+import codecs
+import struct
+import errno
+import argparse
+import re
+import base64
+from binascii import unhexlify
+def parse_args():
+    parser = argparse.ArgumentParser(description=(
+        "Helper - Specify input file to analysis and output folder to save corpdirus for constants in the overall project -------  Example usage : python2 thisfile.py outdir o.txt"))
+    parser.add_argument("corpdir",
+        help="The path to the corpus directory to generate files.")
+    parser.add_argument("infile",
+        help="Specify file output of codeql analysis - ex. ooo-hex.txt, analysis take place on this file, example : python2 thisfile.py outdir out.txt")
+    return parser.parse_args()    
+def ensure_dir(dir):
+    try:
+        os.makedirs(dir)
+    except OSError as e:
+        if e.errno == errno.EEXIST:
+            #print "[-] Directory exists, specify another directory"
+            exit(1)
+def do_analysis1(corpdir, infile):
+    with open(infile, "rb") as f:        
+        lines = f.readlines()[1:]       
+        f.close()       
+        new_lst = []
+        n = 1
+        for i, num in enumerate(lines):
+            if i != 0:
+                new_lst.append(num)                               
+                str1 = str(num)
+                print ("num is " + str1)
+                str1 = str1.rstrip('\n\n')
+                #str1 = str1.replace("0x","");
+                str1 = str1.replace("|","")
+                str1 = str1.rstrip('\r\n')
+                str1 = str1.rstrip('\n')
+                str1 = str1.replace(" ","")
+                    #str1 = str1.translate(None, string.punctuation)
+                translator=str.maketrans('','',string.punctuation)
+                str1=str1.translate(translator)
+                str1 = str1[1:]
+                str1 = str1[:-1]
+                print("After cleanup : " + str1)
+                if (str1 != '0') and (str1 != 'ffffffff') and (str1 != 'fffffffe') or (len(str1) == 4) or (len(str1) == 8):
+                    print ("first : "+str1)
+                    if len(str1) > 8 :
+                        str1 = str1[:-1]
+                    elif (len(str1) == 5) :
+                        str1 = str1 = "0"
+                    try:
+                            #str1 = str1.decode("hex")
+                            with open(corpdir+'/lit-seed{0}'.format(n), 'w') as file:                    
+                                    str1 = str1.replace("0x","");
+                                    print (str1)                                    
+                                    str1 = int(str1,base=16)                                    
+                                    str1 = str1.to_bytes(4, byteorder='little')                                                          
+                                    file.write(str(str1))                                    
+                                    file.close()
+                                    with open (corpdir+'/lit-seed{0}'.format(n), 'r') as q :
+                                        a = q.readline()                                        
+                                        a = a[1:]
+                                        print ("AFL++ Autodict-QL by Microsvuln : Writing Token :" + str(a))
+                                        q.close()
+                                        with open (corpdir+'/lit-seed{0}'.format(n), 'w') as w1 :
+                                                w1.write(str(a))
+                                                print ("Done!")
+                                                w1.close()                                                                                
+                    except:                                 
+                            print("Error!") 
+                    n = n+1
+
+def main():
+    args = parse_args()    
+    ensure_dir(args.corpdir)
+    do_analysis1(args.corpdir, args.infile)
+if __name__ == '__main__':
+    main()
\ No newline at end of file
diff --git a/utils/autodict_ql/qlpack.yml b/utils/autodict_ql/qlpack.yml
new file mode 100644
index 00000000..c037a344
--- /dev/null
+++ b/utils/autodict_ql/qlpack.yml
@@ -0,0 +1,3 @@
+name: automate
+version: 0.0.0
+libraryPathDependencies: codeql-cpp
diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
new file mode 100644
index 00000000..77a15f8e
--- /dev/null
+++ b/utils/autodict_ql/readme.md
@@ -0,0 +1,81 @@
+# Autodict-QL - Optimal Token Generation for Fuzzing
+
+## What is this?
+
+Autodict-QL is a plugin system that enables fast generation of Tokens/Dictionaries in a handy way that can be manipulated by the user (Unlike The LLVM Passes that are hard to modify). This means that autodict-ql is a scriptable feature which basically uses the CodeQL (A powerful semantic code analysis engine) to fetch information from a code base.
+
+Tokens are useful when you perform fuzzing on different parsers. AFL++ `-x` switch enables the usage of dictionaries through your fuzzing campagin. if you are not familiar with Dictionaries in fuzzing, take a look [here](https://github.com/AFLplusplus/AFLplusplus/tree/stable/dictionaries) .
+
+
+## Why CodeQL ?
+We basically developed this plugin on top of CodeQL engine because it gives the user scripting features, it's easier and it's independent of the LLVM system. This means that a user can write his CodeQL scripts or modify the current scripts to improve or change the token generation algorithms based on different program analysis concepts.
+
+
+## CodeQL scripts
+Currently, we pushed some scripts as defaults for Token generation. In addition, we provide every CodeQL script as an standalone script because it's easier to modify or test.
+
+Currently we provided the following CodeQL scripts :
+
+`strcmp-str.ql` is used to extract strings that are related to `strcmp` function.
+
+`strncmp-str.ql` is used to extract the strings from the `strncmp` function.
+
+`memcmp-str.ql` is used to extract the strings from the `memcmp` function.
+
+`litool.ql` extracts Magic numbers as Hexadecimal format.
+
+`strtool.ql` extracts strings with uses of a regex and dataflow concept to capture the string comparison functions. if strcmp is rewritten in a project as Mystrcmp or something like strmycmp, then this script can catch the arguments and these are valuable tokens.
+
+You can write other CodeQL scripts to extract possible effective tokens if you think they can be useful.
+
+
+## Usage
+The usage of Autodict-QL is pretty easy. But let's describe it as :
+
+1. First of all, you need to have CodeQL installed on the system. we make this possible with `build-codeql.sh` bash script. This script will install CodeQL completety and will set the required environment variables for your system, so :
+
+` # chmod +x codeql-build.sh`
+
+` # codeql `
+
+Then you should get :
+
+` Usage: codeql <command> <argument>...
+Create and query CodeQL databases, or work with the QL language.
+
+GitHub makes this program freely available for the analysis of open-source software and certain other uses, but it is
+not itself free software. Type codeql --license to see the license terms.
+
+      --license              Show the license terms for the CodeQL toolchain.
+Common options:
+  -h, --help                 Show this help text.
+  -v, --verbose              Incrementally increase the number of progress messages printed.
+  -q, --quiet                Incrementally decrease the number of progress messages printed.
+Some advanced options have been hidden; try --help -v for a fuller view.
+Commands:
+  query     Compile and execute QL code.
+  bqrs      Get information from .bqrs files.
+  database  Create, analyze and process CodeQL databases.
+  dataset   [Plumbing] Work with raw QL datasets.
+  test      Execute QL unit tests.
+  resolve   [Deep plumbing] Helper commands to resolve disk locations etc.
+  execute   [Deep plumbing] Low-level commands that need special JVM options.
+  version   Show the version of the CodeQL toolchain.
+  generate  Generate formatted QL documentation.
+  github    Commands useful for interacting with the GitHub API through CodeQL.
+`
+
+2. Compiler your project with CodeQL: For using the Autodict-QL plugin, you need to compile the source of the target you want to fuzz with CodeQL. This is not something hard .
+	- First you need to create a CodeQL database of the project codebase, suppose we want to compile the libxml with codeql. go to libxml and issue the following commands:
+		- `./configure --disable-shared`
+		- `codeql create database libxml-db --language=cpp --command=make
+			- Now you have the CodeQL database of the project :-)
+3. To run the Autodict-QL, the final step is to just create a folder named `automate` in the project you want to fuzz.
+	- `mkdir automate` (inside the libxml directory)
+4. The final step is to update the CodeQL database you created in the step 2 inside the automate dir you created at step 3 :
+	- `codeql database upgrade ../libxml-db`
+5. Everything is set! :-), now you should issue the following to get the tokens :
+		- `python3 autodict-ql.py [CURRECT_DIR] [CODEQL_DATABASE_PATH] [TOKEN_PATH]`
+			- example : `python3 autodict-ql.py /home/user/libxml/automate /home/user/libxml/libxml-db tokens`
+				- This will create the final `tokens` dir for you and you are done, then pass the tokens path to afl `-x` flag.
+6. Done! 
\ No newline at end of file
diff --git a/utils/autodict_ql/strtool.ql b/utils/autodict_ql/strtool.ql
index f78aabbb..253d1555 100644
--- a/utils/autodict_ql/strtool.ql
+++ b/utils/autodict_ql/strtool.ql
@@ -3,8 +3,8 @@ import semmle.code.cpp.dataflow.DataFlow
 class StringLiteralNode extends DataFlow::Node {
   StringLiteralNode() { this.asExpr() instanceof StringLiteral }
 }
-class MemcmpArgNode extends DataFlow::Node {
-   MemcmpArgNode() {
+class CmpArgNode extends DataFlow::Node {
+   CmpArgNode() {
     exists(FunctionCall fc |
       fc.getTarget().getName().regexpMatch(".*(str|mem|strn|b)*(cmp|str)*") and
       fc.getArgument(0) = this.asExpr() 
@@ -17,7 +17,7 @@ class MemcmpArgNode extends DataFlow::Node {
   }
 }
 
-from StringLiteralNode src, MemcmpArgNode arg
+from StringLiteralNode src, CmpArgNode arg
 where
   DataFlow::localFlow(src, arg)
 

From 6088a0d4c2aeada7d952ce05bc1e683b858b1ade Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 02:04:17 +0400
Subject: [PATCH 03/25] update readme

update readme
---
 utils/autodict_ql/readme.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index 77a15f8e..a610afb7 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -40,7 +40,7 @@ The usage of Autodict-QL is pretty easy. But let's describe it as :
 
 Then you should get :
 
-` Usage: codeql <command> <argument>...
+' Usage: codeql <command> <argument>...
 Create and query CodeQL databases, or work with the QL language.
 
 GitHub makes this program freely available for the analysis of open-source software and certain other uses, but it is
@@ -63,7 +63,7 @@ Commands:
   version   Show the version of the CodeQL toolchain.
   generate  Generate formatted QL documentation.
   github    Commands useful for interacting with the GitHub API through CodeQL.
-`
+'
 
 2. Compiler your project with CodeQL: For using the Autodict-QL plugin, you need to compile the source of the target you want to fuzz with CodeQL. This is not something hard .
 	- First you need to create a CodeQL database of the project codebase, suppose we want to compile the libxml with codeql. go to libxml and issue the following commands:

From cabde32140d6b781fea3c81e535b717bd01b1ec7 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 02:06:18 +0400
Subject: [PATCH 04/25] Update readme

Update readme
---
 utils/autodict_ql/readme.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index a610afb7..82aa0a23 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -68,7 +68,7 @@ Commands:
 2. Compiler your project with CodeQL: For using the Autodict-QL plugin, you need to compile the source of the target you want to fuzz with CodeQL. This is not something hard .
 	- First you need to create a CodeQL database of the project codebase, suppose we want to compile the libxml with codeql. go to libxml and issue the following commands:
 		- `./configure --disable-shared`
-		- `codeql create database libxml-db --language=cpp --command=make
+		- `codeql create database libxml-db --language=cpp --command=make`
 			- Now you have the CodeQL database of the project :-)
 3. To run the Autodict-QL, the final step is to just create a folder named `automate` in the project you want to fuzz.
 	- `mkdir automate` (inside the libxml directory)

From 01658fb2e8d923c2d3df225249d9e8e0931511e8 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 02:07:24 +0400
Subject: [PATCH 05/25] Update readme

Update readme
---
 utils/autodict_ql/readme.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index 82aa0a23..e8d3c761 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -70,8 +70,8 @@ Commands:
 		- `./configure --disable-shared`
 		- `codeql create database libxml-db --language=cpp --command=make`
 			- Now you have the CodeQL database of the project :-)
-3. To run the Autodict-QL, the final step is to just create a folder named `automate` in the project you want to fuzz.
-	- `mkdir automate` (inside the libxml directory)
+3. To run the Autodict-QL, the final step is to just create a folder named `automate` in the project you want to fuzz. (inside the libxml directory)
+	- `mkdir automate` 
 4. The final step is to update the CodeQL database you created in the step 2 inside the automate dir you created at step 3 :
 	- `codeql database upgrade ../libxml-db`
 5. Everything is set! :-), now you should issue the following to get the tokens :

From 7a383342de6687a09b46151c1f3cf0d44810995a Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 02:07:52 +0400
Subject: [PATCH 06/25] rename python file

rename python file
---
 utils/autodict_ql/{autodict_ql.py => autodict-ql.py} | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 rename utils/autodict_ql/{autodict_ql.py => autodict-ql.py} (100%)

diff --git a/utils/autodict_ql/autodict_ql.py b/utils/autodict_ql/autodict-ql.py
similarity index 100%
rename from utils/autodict_ql/autodict_ql.py
rename to utils/autodict_ql/autodict-ql.py

From 67989e9f2acb5e39e9ef422c27f0fe9db3f7da95 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 02:09:38 +0400
Subject: [PATCH 07/25] update

update
---
 utils/autodict_ql/readme.md | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index e8d3c761..b368002c 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -40,7 +40,8 @@ The usage of Autodict-QL is pretty easy. But let's describe it as :
 
 Then you should get :
 
-' Usage: codeql <command> <argument>...
+" 
+Usage: codeql <command> <argument>...
 Create and query CodeQL databases, or work with the QL language.
 
 GitHub makes this program freely available for the analysis of open-source software and certain other uses, but it is
@@ -63,7 +64,7 @@ Commands:
   version   Show the version of the CodeQL toolchain.
   generate  Generate formatted QL documentation.
   github    Commands useful for interacting with the GitHub API through CodeQL.
-'
+"
 
 2. Compiler your project with CodeQL: For using the Autodict-QL plugin, you need to compile the source of the target you want to fuzz with CodeQL. This is not something hard .
 	- First you need to create a CodeQL database of the project codebase, suppose we want to compile the libxml with codeql. go to libxml and issue the following commands:
@@ -74,7 +75,7 @@ Commands:
 	- `mkdir automate` 
 4. The final step is to update the CodeQL database you created in the step 2 inside the automate dir you created at step 3 :
 	- `codeql database upgrade ../libxml-db`
-5. Everything is set! :-), now you should issue the following to get the tokens :
+5. Everything is set! Now you should issue the following to get the tokens :
 		- `python3 autodict-ql.py [CURRECT_DIR] [CODEQL_DATABASE_PATH] [TOKEN_PATH]`
 			- example : `python3 autodict-ql.py /home/user/libxml/automate /home/user/libxml/libxml-db tokens`
 				- This will create the final `tokens` dir for you and you are done, then pass the tokens path to afl `-x` flag.

From c4f418c3b27bad3cc61eb61e7b9cf6fb7bbe6868 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 02:12:24 +0400
Subject: [PATCH 08/25] Add shell command

Add shell command
---
 utils/autodict_ql/readme.md | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index b368002c..c9c0d2d0 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -40,7 +40,7 @@ The usage of Autodict-QL is pretty easy. But let's describe it as :
 
 Then you should get :
 
-" 
+```shell
 Usage: codeql <command> <argument>...
 Create and query CodeQL databases, or work with the QL language.
 
@@ -64,7 +64,7 @@ Commands:
   version   Show the version of the CodeQL toolchain.
   generate  Generate formatted QL documentation.
   github    Commands useful for interacting with the GitHub API through CodeQL.
-"
+```
 
 2. Compiler your project with CodeQL: For using the Autodict-QL plugin, you need to compile the source of the target you want to fuzz with CodeQL. This is not something hard .
 	- First you need to create a CodeQL database of the project codebase, suppose we want to compile the libxml with codeql. go to libxml and issue the following commands:
@@ -76,7 +76,7 @@ Commands:
 4. The final step is to update the CodeQL database you created in the step 2 inside the automate dir you created at step 3 :
 	- `codeql database upgrade ../libxml-db`
 5. Everything is set! Now you should issue the following to get the tokens :
-		- `python3 autodict-ql.py [CURRECT_DIR] [CODEQL_DATABASE_PATH] [TOKEN_PATH]`
-			- example : `python3 autodict-ql.py /home/user/libxml/automate /home/user/libxml/libxml-db tokens`
-				- This will create the final `tokens` dir for you and you are done, then pass the tokens path to afl `-x` flag.
+	- `python3 autodict-ql.py [CURRECT_DIR] [CODEQL_DATABASE_PATH] [TOKEN_PATH]`
+		- example : `python3 autodict-ql.py /home/user/libxml/automate /home/user/libxml/libxml-db tokens`
+			- This will create the final `tokens` dir for you and you are done, then pass the tokens path to afl `-x` flag.
 6. Done! 
\ No newline at end of file

From bc99b5ba03815e2cfd2a6314a2fa9da78baa6fb6 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 02:13:18 +0400
Subject: [PATCH 09/25] update readme

update readme
---
 utils/autodict_ql/readme.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index c9c0d2d0..c8e5556f 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -2,7 +2,7 @@
 
 ## What is this?
 
-Autodict-QL is a plugin system that enables fast generation of Tokens/Dictionaries in a handy way that can be manipulated by the user (Unlike The LLVM Passes that are hard to modify). This means that autodict-ql is a scriptable feature which basically uses the CodeQL (A powerful semantic code analysis engine) to fetch information from a code base.
+`Autodict-QL` is a plugin system that enables fast generation of Tokens/Dictionaries in a handy way that can be manipulated by the user (Unlike The LLVM Passes that are hard to modify). This means that autodict-ql is a scriptable feature which basically uses the CodeQL (A powerful semantic code analysis engine) to fetch information from a code base.
 
 Tokens are useful when you perform fuzzing on different parsers. AFL++ `-x` switch enables the usage of dictionaries through your fuzzing campagin. if you are not familiar with Dictionaries in fuzzing, take a look [here](https://github.com/AFLplusplus/AFLplusplus/tree/stable/dictionaries) .
 

From b418c31479f5d5e1d10c75eafec9ead9351453cb Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 02:39:09 +0400
Subject: [PATCH 10/25] Some updates on readme

Some updates on readme
---
 utils/autodict_ql/readme.md | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index c8e5556f..45f685c6 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -79,4 +79,19 @@ Commands:
 	- `python3 autodict-ql.py [CURRECT_DIR] [CODEQL_DATABASE_PATH] [TOKEN_PATH]`
 		- example : `python3 autodict-ql.py /home/user/libxml/automate /home/user/libxml/libxml-db tokens`
 			- This will create the final `tokens` dir for you and you are done, then pass the tokens path to afl `-x` flag.
-6. Done! 
\ No newline at end of file
+6. Done! 
+
+
+## More on dictionaries and tokens
+Core developer of the AFL++ project Marc Heuse also developed a similar tool named `dict2file` which is a LLVM pass which can automatically extracts useful tokens, in addition with LTO instrumentation mode, this dict2file is automtically generates token extraction.
+On the other hand, you can also use Google dictionaries which have been made public in May 2020, but the problem of using Google dictionaries is that they are limited to specific file format and speicifications. for example, for testing binutils and ELF file format or AVI in FFMPEG, there are no prebuilt dictionary, so it is highly recommended to use `Autodict-QL` or `Dict2File` features to automatically generating dictionaries based on the target.
+
+I've personally prefer to use `Autodict-QL` or `dict2file` rather than Google dictionaries or any other manully generated dictionaries as `Autodict-QL` is working based on the target.
+In overall, fuzzing with dictionaries and well-generated tokens will give better results.
+
+There are 2 important points to remember :
+
+- If you combine `Autodict-QL` with AFL++ cmplog, you will get much better code coverage and hence better chance to discover new bugs.
+- Do not remember to set the `AFL_MAX_DET_EXTRAS` to the number of generated dictionaries, if you forget to set this environment variable, then AFL++ use just 200 tokens and use the rest of them probablistically. So this will guarantees that your tokens will be used by AFL++.
+
+ 
\ No newline at end of file

From b7d12c8532da0a094aa2504e90f84a1530d569a9 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 02:45:46 +0400
Subject: [PATCH 11/25] Update readme

Update readme
---
 utils/autodict_ql/readme.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index 45f685c6..39857f69 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -83,7 +83,7 @@ Commands:
 
 
 ## More on dictionaries and tokens
-Core developer of the AFL++ project Marc Heuse also developed a similar tool named `dict2file` which is a LLVM pass which can automatically extracts useful tokens, in addition with LTO instrumentation mode, this dict2file is automtically generates token extraction.
+Core developer of the AFL++ project Marc Heuse also developed a similar tool named `dict2file` which is a LLVM pass which can automatically extracts useful tokens, in addition with LTO instrumentation mode, this dict2file is automtically generates token extraction. `Autodict-QL` plugin gives you scripting capability and you can do whatever you want to extract from the Codebase and it's up to you. in addition it's independent from LLVM system.
 On the other hand, you can also use Google dictionaries which have been made public in May 2020, but the problem of using Google dictionaries is that they are limited to specific file format and speicifications. for example, for testing binutils and ELF file format or AVI in FFMPEG, there are no prebuilt dictionary, so it is highly recommended to use `Autodict-QL` or `Dict2File` features to automatically generating dictionaries based on the target.
 
 I've personally prefer to use `Autodict-QL` or `dict2file` rather than Google dictionaries or any other manully generated dictionaries as `Autodict-QL` is working based on the target.

From 8f9d1fd7b05f916d8c43d5872be54d9074bdf8db Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 03:16:13 +0400
Subject: [PATCH 12/25] Updates

update
---
 utils/autodict_ql/readme.md | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index 39857f69..3e4655c8 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -34,10 +34,11 @@ The usage of Autodict-QL is pretty easy. But let's describe it as :
 
 1. First of all, you need to have CodeQL installed on the system. we make this possible with `build-codeql.sh` bash script. This script will install CodeQL completety and will set the required environment variables for your system, so :
 
-` # chmod +x codeql-build.sh`
-
-` # codeql `
-
+```shell
+# chmod +x codeql-build.sh`
+# sudo ./codeql-build.sh
+# codeql `
+```
 Then you should get :
 
 ```shell
@@ -93,5 +94,3 @@ There are 2 important points to remember :
 
 - If you combine `Autodict-QL` with AFL++ cmplog, you will get much better code coverage and hence better chance to discover new bugs.
 - Do not remember to set the `AFL_MAX_DET_EXTRAS` to the number of generated dictionaries, if you forget to set this environment variable, then AFL++ use just 200 tokens and use the rest of them probablistically. So this will guarantees that your tokens will be used by AFL++.
-
- 
\ No newline at end of file

From 4291c3db5dca5082aed123f3a353f8af4a0f4785 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 14:04:06 +0400
Subject: [PATCH 13/25] finalize 1

commit final things
---
 utils/autodict_ql/autodict-ql.py | 87 ++++++--------------------------
 utils/autodict_ql/readme.md      |  6 ++-
 2 files changed, 20 insertions(+), 73 deletions(-)

diff --git a/utils/autodict_ql/autodict-ql.py b/utils/autodict_ql/autodict-ql.py
index 69d11f48..ddc95435 100644
--- a/utils/autodict_ql/autodict-ql.py
+++ b/utils/autodict_ql/autodict-ql.py
@@ -1,4 +1,14 @@
 #!/usr/bin/env python3
+# AutoDict-QL - Optimal Token Generation for Fuzzing
+# Part of AFL++ Project
+# Developed and Maintained by Arash Ale Ebrahim (@Microsvuln)
+# Usage : python3 autodict-ql.py [CURRECT_DIR] [CODEQL_DATABASE_PATH] [TOKEN_PATH]
+# CURRENT_DIR = full of your current Dir
+# CODEQL_DATABASE_PATH = Full path to your CodeQL database
+# TOKEN_PATH = Folder name of the newly generated tokens
+# Example : python3 autodict-ql.py /home/user/libxml/automate /home/user/libxml/libxml-db tokens
+# Just pass the tokens folder to the -x flag of your fuzzer
+
 import os
 import string
 import binascii 
@@ -42,47 +52,25 @@ def static_analysis(file,file2,cur,db) :
         f.close()
 
 def copy_tokens(cur, tokenpath) :
-    subprocess.call(["cp " + cur  + "/" + "arrays-lits/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
-    subprocess.call(["cp " + cur  + "/" + "strstr-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
     subprocess.call(["cp " + cur  + "/" + "strcmp-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
     subprocess.call(["cp " + cur  + "/" + "strncmp-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
-    subprocess.call(["cp " + cur  + "/" + "local-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
     subprocess.call(["cp " + cur  + "/" + "memcmp-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
-    subprocess.call(["cp " + cur  + "/" + "global-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
     subprocess.call(["cp " + cur  + "/" + "lits/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
-    subprocess.call(["cp " + cur  + "/" + "arrays-lits/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
-    subprocess.call(["cp " + cur  + "/" + "arrays-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
     subprocess.call(["cp " + cur  + "/" + "strtool-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
-    #strtool-strs
+
 
 
 def codeql_analysis(cur, db) :
     static_analysis("litout.out","litool.ql", cur, db)
     static_analysis("strcmp-strings.out","strcmp-str.ql", cur, db)
     static_analysis("strncmp-strings.out","strncmp-str.ql", cur, db)
-    static_analysis("strstr-strings.out","strstr-str.ql", cur, db)
     static_analysis("memcmp-strings.out","memcmp-str.ql", cur, db)
-    static_analysis("global-values-strings.out","globals-values.ql", cur, db)
-    static_analysis("local-strings.out","locals-strs.ql", cur, db)
     static_analysis("strtool-strings.out","strtool.ql", cur, db)
-    static_analysis("arrays.out","array-literals.ql", cur, db)
-    start_aflql(0,cur)
-    #command1 = [
-    #       'codeql','query', 'run',
-    #       cur + '/litool.ql',
-    #       '-d',
-    #       db, '>','fff.txt'
-    #    ]
-    #with open("litool2.log", "w") as f:
-    #    stream = os.popen("codeql query run litool.ql -d " + db )
-    #    output = stream.read()
-    #    f.write(output)
-    #    f.close()
-    #worker1 = subprocess.Popen(command1)
-    #print(worker1.communicate())
+    start_autodict(0,cur)
 
 
-def start_aflql(tokenpath, cur):
+
+def start_autodict(tokenpath, cur):
     command = [
            'python3',
            cur + '/litan.py',
@@ -110,23 +98,6 @@ def start_aflql(tokenpath, cur):
     worker3 = subprocess.Popen(command2)
     print(worker3.communicate())
 
-    command3 = [
-           'python3',
-           cur + '/array-lits.py',
-           cur + '/arrays-lits/',
-           cur + '/arrays.out'
-        ]
-    worker4 = subprocess.Popen(command3)
-    print(worker4.communicate())
-
-    command4 = [
-           'python3',
-           cur + '/array-strings.py',
-           cur + '/arrays-strs/',
-           cur + '/arrays.out'
-        ]
-    worker5 = subprocess.Popen(command4)
-    print(worker5.communicate())
 
 
     command5 = [
@@ -138,26 +109,7 @@ def start_aflql(tokenpath, cur):
     worker6 = subprocess.Popen(command5)
     print(worker6.communicate())
 
-    command6 = [
-           'python3',
-           cur + '/globals-strings.py',
-           cur + '/global-strs/',
-           cur + '/global-values-strings.out'
-        ]
-    worker7 = subprocess.Popen(command6)
-    print(worker7.communicate())
 
-    command7 = [
-           'python3',
-           cur + '/strstr-strings.py',
-           cur + '/strstr-strs/',
-           cur + '/strstr-strings.out'
-        ]
-    worker8 = subprocess.Popen(command7)
-    print(worker8.communicate())
-
-
-    #strtool-strings.out
 
     command8 = [
            'python3',
@@ -168,14 +120,7 @@ def start_aflql(tokenpath, cur):
     worker9 = subprocess.Popen(command8)
     print(worker9.communicate())
 
-    command9 = [
-           'python3',
-           cur + '/local-strings.py',
-           cur + '/local-strs/',
-           cur + '/local-strings.out'
-        ]
-    worker10 = subprocess.Popen(command9)
-    print(worker10.communicate())
+
 
 def main():
     args = parse_args()    
@@ -183,6 +128,6 @@ def main():
     #copy_tokens(args.cur, args.tokenpath)
     codeql_analysis(args.cur, args.db)
     copy_tokens(args.cur, args.tokenpath)
-    #start_aflql(args.tokenpath, args.cur)
+    #start_autodict(args.tokenpath, args.cur)
 if __name__ == '__main__':
     main()
\ No newline at end of file
diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index 3e4655c8..f8d23098 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -67,7 +67,7 @@ Commands:
   github    Commands useful for interacting with the GitHub API through CodeQL.
 ```
 
-2. Compiler your project with CodeQL: For using the Autodict-QL plugin, you need to compile the source of the target you want to fuzz with CodeQL. This is not something hard .
+2. Compile your project with CodeQL: For using the Autodict-QL plugin, you need to compile the source of the target you want to fuzz with CodeQL. This is not something hard .
 	- First you need to create a CodeQL database of the project codebase, suppose we want to compile the libxml with codeql. go to libxml and issue the following commands:
 		- `./configure --disable-shared`
 		- `codeql create database libxml-db --language=cpp --command=make`
@@ -87,10 +87,12 @@ Commands:
 Core developer of the AFL++ project Marc Heuse also developed a similar tool named `dict2file` which is a LLVM pass which can automatically extracts useful tokens, in addition with LTO instrumentation mode, this dict2file is automtically generates token extraction. `Autodict-QL` plugin gives you scripting capability and you can do whatever you want to extract from the Codebase and it's up to you. in addition it's independent from LLVM system.
 On the other hand, you can also use Google dictionaries which have been made public in May 2020, but the problem of using Google dictionaries is that they are limited to specific file format and speicifications. for example, for testing binutils and ELF file format or AVI in FFMPEG, there are no prebuilt dictionary, so it is highly recommended to use `Autodict-QL` or `Dict2File` features to automatically generating dictionaries based on the target.
 
-I've personally prefer to use `Autodict-QL` or `dict2file` rather than Google dictionaries or any other manully generated dictionaries as `Autodict-QL` is working based on the target.
+I've personally prefer to use `Autodict-QL` or `dict2file` rather than Google dictionaries or any other manully generated dictionaries as `Autodict-QL` and `dict2file` is working based on the target.
 In overall, fuzzing with dictionaries and well-generated tokens will give better results.
 
 There are 2 important points to remember :
 
 - If you combine `Autodict-QL` with AFL++ cmplog, you will get much better code coverage and hence better chance to discover new bugs.
 - Do not remember to set the `AFL_MAX_DET_EXTRAS` to the number of generated dictionaries, if you forget to set this environment variable, then AFL++ use just 200 tokens and use the rest of them probablistically. So this will guarantees that your tokens will be used by AFL++.
+
+Thanks are going to Marc Heuse, the AFL++ main developer, Antonio Morales and Stefan Nagy
\ No newline at end of file

From 7f6d256014ae6728bc938e33b7038105a5714c9b Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 14:06:12 +0400
Subject: [PATCH 14/25] space

space
---
 utils/autodict_ql/readme.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index f8d23098..0449233b 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -30,6 +30,7 @@ You can write other CodeQL scripts to extract possible effective tokens if you t
 
 
 ## Usage
+
 The usage of Autodict-QL is pretty easy. But let's describe it as :
 
 1. First of all, you need to have CodeQL installed on the system. we make this possible with `build-codeql.sh` bash script. This script will install CodeQL completety and will set the required environment variables for your system, so :

From 7a3dfbce71d45742a6b571e41f07ae6b104e3a6b Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 14:07:13 +0400
Subject: [PATCH 15/25] remove things

remove things
---
 utils/autodict_ql/readme.md | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index 0449233b..9e6a7292 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -36,9 +36,9 @@ The usage of Autodict-QL is pretty easy. But let's describe it as :
 1. First of all, you need to have CodeQL installed on the system. we make this possible with `build-codeql.sh` bash script. This script will install CodeQL completety and will set the required environment variables for your system, so :
 
 ```shell
-# chmod +x codeql-build.sh`
+# chmod +x codeql-build.sh
 # sudo ./codeql-build.sh
-# codeql `
+# codeql 
 ```
 Then you should get :
 

From 8d894eec90ef738702d42274cda0d6a4e5494627 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 14:11:33 +0400
Subject: [PATCH 16/25] Add python scripts

Add python scripts
---
 utils/autodict_ql/memcmp-strings.py  | 64 ++++++++++++++++++++++++++++
 utils/autodict_ql/stan-strings.py    | 60 ++++++++++++++++++++++++++
 utils/autodict_ql/strcmp-strings.py  | 60 ++++++++++++++++++++++++++
 utils/autodict_ql/strncmp-strings.py | 64 ++++++++++++++++++++++++++++
 4 files changed, 248 insertions(+)
 create mode 100644 utils/autodict_ql/memcmp-strings.py
 create mode 100644 utils/autodict_ql/stan-strings.py
 create mode 100644 utils/autodict_ql/strcmp-strings.py
 create mode 100644 utils/autodict_ql/strncmp-strings.py

diff --git a/utils/autodict_ql/memcmp-strings.py b/utils/autodict_ql/memcmp-strings.py
new file mode 100644
index 00000000..e948fba4
--- /dev/null
+++ b/utils/autodict_ql/memcmp-strings.py
@@ -0,0 +1,64 @@
+#!/usr/bin/env python3
+# Autodict-QL - Optimal token generation for fuzzing
+# Part of AFL++ Project
+# Author : Microsvuln - Arash.vre@gmail.com
+
+import os
+import string
+import binascii 
+import codecs
+import errno
+import struct
+import argparse
+import re
+from binascii import unhexlify
+
+def ensure_dir(dir):
+    try:
+        os.makedirs(dir)
+    except OSError as e:
+        if e.errno != errno.EEXIST:
+            raise
+
+def parse_args():
+    parser = argparse.ArgumentParser(description=(
+        "Helper - Specify input file analysis and output folder to save corpus for strings in the overall project ---------------------------------------------------------------------------  Example usage : python2 thisfile.py outdir str.txt"    ))
+    parser.add_argument("corpdir",
+        help="The path to the corpus directory to generate strings.")
+    parser.add_argument("infile",
+        help="Specify file output of codeql analysis - ex. ooo-atr.txt, analysis take place on this file, example : python2 thisfile.py outdir strings.txt")
+
+    return parser.parse_args()
+
+
+def do_string_analysis(corpdir, infile1):
+    with open(infile1, "r") as f1:        
+        lines = f1.readlines()[1:]       
+        f1.close()       
+        new_lst1 = []
+        n = 1
+        for i, num1 in enumerate(lines):
+            if i != 0:
+                new_lst1.append(num1)
+                print("num : %s" % num1)
+                str11 = str(num1)
+                str11 = str11.replace("|","")
+                str11 = str11.replace("\n","")
+                str11 = str11.lstrip()
+                str11 = str11.rstrip()
+                print("all strings : %s" % str11)
+                str11 = str(str11)
+                if ((" " in str11 ) or (")" in str11) or ("(" in str11)):                    
+                    print("Space / Paranthesis String : %s" % str11)
+                else :
+                    with open(corpdir+'/memcmp-str{0}'.format(n), 'w') as file:                    
+                            file.write(str11)
+                            print("Hahaha : %s" % str11)
+                            n=n+1
+
+def main():
+    args = parse_args()    
+    ensure_dir(args.corpdir)
+    do_string_analysis(args.corpdir, args.infile)
+if __name__ == '__main__':
+    main()
\ No newline at end of file
diff --git a/utils/autodict_ql/stan-strings.py b/utils/autodict_ql/stan-strings.py
new file mode 100644
index 00000000..c35d8a65
--- /dev/null
+++ b/utils/autodict_ql/stan-strings.py
@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+import os
+import string
+import binascii 
+import codecs
+import errno
+import struct
+import argparse
+import re
+from binascii import unhexlify
+
+def ensure_dir(dir):
+    try:
+        os.makedirs(dir)
+    except OSError as e:
+        if e.errno != errno.EEXIST:
+            raise
+
+def parse_args():
+    parser = argparse.ArgumentParser(description=(
+        "Helper - Specify input file analysis and output folder to save corpus for strings in the overall project ---------------------------------------------------------------------------  Example usage : python2 thisfile.py outdir str.txt"    ))
+    parser.add_argument("corpdir",
+        help="The path to the corpus directory to generate strings.")
+    parser.add_argument("infile",
+        help="Specify file output of codeql analysis - ex. ooo-atr.txt, analysis take place on this file, example : python2 thisfile.py outdir strings.txt")
+
+    return parser.parse_args()
+
+
+def do_string_analysis(corpdir, infile1):
+    with open(infile1, "r") as f1:        
+        lines = f1.readlines()[1:]       
+        f1.close()       
+        new_lst1 = []
+        n = 1
+        for i, num1 in enumerate(lines):
+            if i != 0:
+                new_lst1.append(num1)
+                print("num : %s" % num1)
+                str11 = str(num1)
+                str11 = str11.replace("|","")
+                str11 = str11.replace("\n","")
+                str11 = str11.lstrip()
+                str11 = str11.rstrip()
+                print("all strings : %s" % str11)
+                str11 = str(str11)
+                if ((" " in str11 ) or (")" in str11) or ("(" in str11)) or ("<" in str11) or (">" in str11) :
+                    print("Space / Paranthesis String : %s" % str11)
+                else :
+                    with open(corpdir+'/seed-str{0}'.format(n), 'w') as file:                    
+                            file.write(str11)
+                            print("Hahaha : %s" % str11)
+                            n=n+1
+
+def main():
+    args = parse_args()    
+    ensure_dir(args.corpdir)
+    do_string_analysis(args.corpdir, args.infile)
+if __name__ == '__main__':
+    main()
\ No newline at end of file
diff --git a/utils/autodict_ql/strcmp-strings.py b/utils/autodict_ql/strcmp-strings.py
new file mode 100644
index 00000000..412b70ae
--- /dev/null
+++ b/utils/autodict_ql/strcmp-strings.py
@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+import os
+import string
+import binascii 
+import codecs
+import errno
+import struct
+import argparse
+import re
+from binascii import unhexlify
+
+def ensure_dir(dir):
+    try:
+        os.makedirs(dir)
+    except OSError as e:
+        if e.errno != errno.EEXIST:
+            raise
+
+def parse_args():
+    parser = argparse.ArgumentParser(description=(
+        "Helper - Specify input file analysis and output folder to save corpus for strings in the overall project ---------------------------------------------------------------------------  Example usage : python2 thisfile.py outdir str.txt"    ))
+    parser.add_argument("corpdir",
+        help="The path to the corpus directory to generate strings.")
+    parser.add_argument("infile",
+        help="Specify file output of codeql analysis - ex. ooo-atr.txt, analysis take place on this file, example : python2 thisfile.py outdir strings.txt")
+
+    return parser.parse_args()
+
+
+def do_string_analysis(corpdir, infile1):
+    with open(infile1, "r") as f1:        
+        lines = f1.readlines()[1:]       
+        f1.close()       
+        new_lst1 = []
+        n = 1
+        for i, num1 in enumerate(lines):
+            if i != 0:
+                new_lst1.append(num1)
+                print("num : %s" % num1)
+                str11 = str(num1)
+                str11 = str11.replace("|","")
+                str11 = str11.replace("\n","")
+                str11 = str11.lstrip()
+                str11 = str11.rstrip()
+                print("all strings : %s" % str11)
+                str11 = str(str11)
+                if ((" " in str11 ) or (")" in str11) or ("(" in str11)):                    
+                    print("Space / Paranthesis String : %s" % str11)
+                else :
+                    with open(corpdir+'/strcmp-str{0}'.format(n), 'w') as file:                    
+                            file.write(str11)
+                            print("Hahaha : %s" % str11)
+                            n=n+1
+
+def main():
+    args = parse_args()    
+    ensure_dir(args.corpdir)
+    do_string_analysis(args.corpdir, args.infile)
+if __name__ == '__main__':
+    main()
\ No newline at end of file
diff --git a/utils/autodict_ql/strncmp-strings.py b/utils/autodict_ql/strncmp-strings.py
new file mode 100644
index 00000000..2c07718e
--- /dev/null
+++ b/utils/autodict_ql/strncmp-strings.py
@@ -0,0 +1,64 @@
+#!/usr/bin/env python3
+# Autodict-QL - Optimal token generation for fuzzing
+# Part of AFL++ Project
+# Author : Microsvuln - Arash.vre@gmail.com
+
+import os
+import string
+import binascii 
+import codecs
+import errno
+import struct
+import argparse
+import re
+from binascii import unhexlify
+
+def ensure_dir(dir):
+    try:
+        os.makedirs(dir)
+    except OSError as e:
+        if e.errno != errno.EEXIST:
+            raise
+
+def parse_args():
+    parser = argparse.ArgumentParser(description=(
+        "Helper - Specify input file analysis and output folder to save corpus for strings in the overall project ---------------------------------------------------------------------------  Example usage : python2 thisfile.py outdir str.txt"    ))
+    parser.add_argument("corpdir",
+        help="The path to the corpus directory to generate strings.")
+    parser.add_argument("infile",
+        help="Specify file output of codeql analysis - ex. ooo-atr.txt, analysis take place on this file, example : python2 thisfile.py outdir strings.txt")
+
+    return parser.parse_args()
+
+
+def do_string_analysis(corpdir, infile1):
+    with open(infile1, "r") as f1:        
+        lines = f1.readlines()[1:]       
+        f1.close()       
+        new_lst1 = []
+        n = 1
+        for i, num1 in enumerate(lines):
+            if i != 0:
+                new_lst1.append(num1)
+                print("num : %s" % num1)
+                str11 = str(num1)
+                str11 = str11.replace("|","")
+                str11 = str11.replace("\n","")
+                str11 = str11.lstrip()
+                str11 = str11.rstrip()
+                print("all strings : %s" % str11)
+                str11 = str(str11)
+                if ((" " in str11 ) or (")" in str11) or ("(" in str11)):                    
+                    print("Space / Paranthesis String : %s" % str11)
+                else :
+                    with open(corpdir+'/strncmp-str{0}'.format(n), 'w') as file:                    
+                            file.write(str11)
+                            print("Hahaha : %s" % str11)
+                            n=n+1
+
+def main():
+    args = parse_args()    
+    ensure_dir(args.corpdir)
+    do_string_analysis(args.corpdir, args.infile)
+if __name__ == '__main__':
+    main()
\ No newline at end of file

From 6c88b6b362ddc06effd8d99c32375ab34028665c Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 14:13:55 +0400
Subject: [PATCH 17/25] Update python scripts

Update python scripts
---
 utils/autodict_ql/memcmp-strings.py  | 2 +-
 utils/autodict_ql/stan-strings.py    | 6 +++++-
 utils/autodict_ql/strcmp-strings.py  | 6 +++++-
 utils/autodict_ql/strncmp-strings.py | 2 +-
 4 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/utils/autodict_ql/memcmp-strings.py b/utils/autodict_ql/memcmp-strings.py
index e948fba4..fb892aff 100644
--- a/utils/autodict_ql/memcmp-strings.py
+++ b/utils/autodict_ql/memcmp-strings.py
@@ -53,7 +53,7 @@ def do_string_analysis(corpdir, infile1):
                 else :
                     with open(corpdir+'/memcmp-str{0}'.format(n), 'w') as file:                    
                             file.write(str11)
-                            print("Hahaha : %s" % str11)
+                            print("AFL++ Autodict-QL by Microsvuln : Writing Token : %s" % str11)
                             n=n+1
 
 def main():
diff --git a/utils/autodict_ql/stan-strings.py b/utils/autodict_ql/stan-strings.py
index c35d8a65..e9f6f0d0 100644
--- a/utils/autodict_ql/stan-strings.py
+++ b/utils/autodict_ql/stan-strings.py
@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# Autodict-QL - Optimal token generation for fuzzing
+# Part of AFL++ Project
+# Author : Microsvuln - Arash.vre@gmail.com
+
 import os
 import string
 import binascii 
@@ -49,7 +53,7 @@ def do_string_analysis(corpdir, infile1):
                 else :
                     with open(corpdir+'/seed-str{0}'.format(n), 'w') as file:                    
                             file.write(str11)
-                            print("Hahaha : %s" % str11)
+                            print("AFL++ Autodict-QL by Microsvuln : Writing Token : %s" % str11)
                             n=n+1
 
 def main():
diff --git a/utils/autodict_ql/strcmp-strings.py b/utils/autodict_ql/strcmp-strings.py
index 412b70ae..a1b7e27c 100644
--- a/utils/autodict_ql/strcmp-strings.py
+++ b/utils/autodict_ql/strcmp-strings.py
@@ -1,4 +1,8 @@
 #!/usr/bin/env python3
+# Autodict-QL - Optimal token generation for fuzzing
+# Part of AFL++ Project
+# Author : Microsvuln - Arash.vre@gmail.com
+
 import os
 import string
 import binascii 
@@ -49,7 +53,7 @@ def do_string_analysis(corpdir, infile1):
                 else :
                     with open(corpdir+'/strcmp-str{0}'.format(n), 'w') as file:                    
                             file.write(str11)
-                            print("Hahaha : %s" % str11)
+                            print("AFL++ Autodict-QL by Microsvuln : Writing Token : %s" % str11)
                             n=n+1
 
 def main():
diff --git a/utils/autodict_ql/strncmp-strings.py b/utils/autodict_ql/strncmp-strings.py
index 2c07718e..2652f66e 100644
--- a/utils/autodict_ql/strncmp-strings.py
+++ b/utils/autodict_ql/strncmp-strings.py
@@ -53,7 +53,7 @@ def do_string_analysis(corpdir, infile1):
                 else :
                     with open(corpdir+'/strncmp-str{0}'.format(n), 'w') as file:                    
                             file.write(str11)
-                            print("Hahaha : %s" % str11)
+                            print("AFL++ Autodict-QL by Microsvuln : Writing Token : %s" % str11)
                             n=n+1
 
 def main():

From 70e975704465672f49273da9f4a8f7e56f745e20 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 15:47:22 +0400
Subject: [PATCH 18/25] new commit - change strings

new commit - change strings
---
 utils/autodict_ql/autodict-ql.py     |  1 +
 utils/autodict_ql/build-codeql.sh    |  4 ++--
 utils/autodict_ql/memcmp-strings.py  |  3 +--
 utils/autodict_ql/readme.md          | 11 ++++++++---
 utils/autodict_ql/stan-strings.py    |  3 +--
 utils/autodict_ql/strcmp-strings.py  |  3 +--
 utils/autodict_ql/strncmp-strings.py |  3 +--
 7 files changed, 15 insertions(+), 13 deletions(-)

diff --git a/utils/autodict_ql/autodict-ql.py b/utils/autodict_ql/autodict-ql.py
index ddc95435..7bba57fc 100644
--- a/utils/autodict_ql/autodict-ql.py
+++ b/utils/autodict_ql/autodict-ql.py
@@ -57,6 +57,7 @@ def copy_tokens(cur, tokenpath) :
     subprocess.call(["cp " + cur  + "/" + "memcmp-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
     subprocess.call(["cp " + cur  + "/" + "lits/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
     subprocess.call(["cp " + cur  + "/" + "strtool-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["find "+tokenpath+" -size 0 -delete"],shell=True)
 
 
 
diff --git a/utils/autodict_ql/build-codeql.sh b/utils/autodict_ql/build-codeql.sh
index ccff932e..450207f6 100644
--- a/utils/autodict_ql/build-codeql.sh
+++ b/utils/autodict_ql/build-codeql.sh
@@ -3,7 +3,6 @@ if [ -d "codeql-home" ]; then
     echo "Exist !"
     exit 1
 fi
-sudo apt install build-essential libtool-bin python3-dev automake git vim wget -y
 mkdir codeql-home
 cd codeql-home
 git clone https://github.com/github/codeql.git codeql-repo
@@ -12,6 +11,7 @@ wget https://github.com/github/codeql-cli-binaries/releases/download/v2.4.6/code
 unzip codeql-linux64.zip 
 mv codeql codeql-cli
 export "PATH=~/codeql-home/codeql-cli/:$PATH"
+echo "export PATH=~/codeql-home/codeql-cli/:$PATH" >> ~/.bashrc
 codeql resolve languages
 codeql resolve qlpacks
-echo "export PATH=~/codeql-home/codeql-cli/:$PATH" >> ~/.bashrc
\ No newline at end of file
+codeql
\ No newline at end of file
diff --git a/utils/autodict_ql/memcmp-strings.py b/utils/autodict_ql/memcmp-strings.py
index fb892aff..2814da5b 100644
--- a/utils/autodict_ql/memcmp-strings.py
+++ b/utils/autodict_ql/memcmp-strings.py
@@ -46,9 +46,8 @@ def do_string_analysis(corpdir, infile1):
                 str11 = str11.replace("\n","")
                 str11 = str11.lstrip()
                 str11 = str11.rstrip()
-                print("all strings : %s" % str11)
                 str11 = str(str11)
-                if ((" " in str11 ) or (")" in str11) or ("(" in str11)):                    
+                if ((" " in str11 ) or (")" in str11) or ("(" in str11) or ("<" in str11) or (">" in str11)) :
                     print("Space / Paranthesis String : %s" % str11)
                 else :
                     with open(corpdir+'/memcmp-str{0}'.format(n), 'w') as file:                    
diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index 9e6a7292..ccc9b0e3 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -31,13 +31,18 @@ You can write other CodeQL scripts to extract possible effective tokens if you t
 
 ## Usage
 
+Before proceed to installation make sure that you have the following packages by installing them :
+```shell
+sudo apt install build-essential libtool-bin python3-dev python3 automake git vim wget -y
+```
 The usage of Autodict-QL is pretty easy. But let's describe it as :
 
-1. First of all, you need to have CodeQL installed on the system. we make this possible with `build-codeql.sh` bash script. This script will install CodeQL completety and will set the required environment variables for your system, so :
-
+1. First of all, you need to have CodeQL installed on the system. we make this possible with `build-codeql.sh` bash script. This script will install CodeQL completety and will set the required environment variables for your system.
+Do the following :
 ```shell
 # chmod +x codeql-build.sh
-# sudo ./codeql-build.sh
+# ./codeql-build.sh
+# source ~/.bashrc
 # codeql 
 ```
 Then you should get :
diff --git a/utils/autodict_ql/stan-strings.py b/utils/autodict_ql/stan-strings.py
index e9f6f0d0..5a863f80 100644
--- a/utils/autodict_ql/stan-strings.py
+++ b/utils/autodict_ql/stan-strings.py
@@ -46,9 +46,8 @@ def do_string_analysis(corpdir, infile1):
                 str11 = str11.replace("\n","")
                 str11 = str11.lstrip()
                 str11 = str11.rstrip()
-                print("all strings : %s" % str11)
                 str11 = str(str11)
-                if ((" " in str11 ) or (")" in str11) or ("(" in str11)) or ("<" in str11) or (">" in str11) :
+                if ((" " in str11 ) or (")" in str11) or ("(" in str11) or ("<" in str11) or (">" in str11)) :
                     print("Space / Paranthesis String : %s" % str11)
                 else :
                     with open(corpdir+'/seed-str{0}'.format(n), 'w') as file:                    
diff --git a/utils/autodict_ql/strcmp-strings.py b/utils/autodict_ql/strcmp-strings.py
index a1b7e27c..1852b947 100644
--- a/utils/autodict_ql/strcmp-strings.py
+++ b/utils/autodict_ql/strcmp-strings.py
@@ -46,9 +46,8 @@ def do_string_analysis(corpdir, infile1):
                 str11 = str11.replace("\n","")
                 str11 = str11.lstrip()
                 str11 = str11.rstrip()
-                print("all strings : %s" % str11)
                 str11 = str(str11)
-                if ((" " in str11 ) or (")" in str11) or ("(" in str11)):                    
+                if ((" " in str11 ) or (")" in str11) or ("(" in str11) or ("<" in str11) or (">" in str11)) :
                     print("Space / Paranthesis String : %s" % str11)
                 else :
                     with open(corpdir+'/strcmp-str{0}'.format(n), 'w') as file:                    
diff --git a/utils/autodict_ql/strncmp-strings.py b/utils/autodict_ql/strncmp-strings.py
index 2652f66e..f00fa3da 100644
--- a/utils/autodict_ql/strncmp-strings.py
+++ b/utils/autodict_ql/strncmp-strings.py
@@ -46,9 +46,8 @@ def do_string_analysis(corpdir, infile1):
                 str11 = str11.replace("\n","")
                 str11 = str11.lstrip()
                 str11 = str11.rstrip()
-                print("all strings : %s" % str11)
                 str11 = str(str11)
-                if ((" " in str11 ) or (")" in str11) or ("(" in str11)):                    
+                if ((" " in str11 ) or (")" in str11) or ("(" in str11) or ("<" in str11) or (">" in str11)) :
                     print("Space / Paranthesis String : %s" % str11)
                 else :
                     with open(corpdir+'/strncmp-str{0}'.format(n), 'w') as file:                    

From d5fc03b71819ed75bd7134584e8f00a7f1010149 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 15:49:17 +0400
Subject: [PATCH 19/25] update qlpack name

update qlpack name
---
 utils/autodict_ql/qlpack.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/utils/autodict_ql/qlpack.yml b/utils/autodict_ql/qlpack.yml
index c037a344..28892f24 100644
--- a/utils/autodict_ql/qlpack.yml
+++ b/utils/autodict_ql/qlpack.yml
@@ -1,3 +1,3 @@
-name: automate
+name: autodict
 version: 0.0.0
 libraryPathDependencies: codeql-cpp

From 050f331c54a7af2fdb2eb1ca33e9dacd9257dbb0 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 16:04:14 +0400
Subject: [PATCH 20/25] remove unessential things

remove unessential things from scripts
---
 utils/autodict_ql/autodict-ql.py     | 10 +++++-----
 utils/autodict_ql/memcmp-strings.py  |  2 +-
 utils/autodict_ql/stan-strings.py    |  2 +-
 utils/autodict_ql/strcmp-strings.py  |  2 +-
 utils/autodict_ql/strncmp-strings.py |  2 +-
 5 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/utils/autodict_ql/autodict-ql.py b/utils/autodict_ql/autodict-ql.py
index 7bba57fc..b51fbb90 100644
--- a/utils/autodict_ql/autodict-ql.py
+++ b/utils/autodict_ql/autodict-ql.py
@@ -52,11 +52,11 @@ def static_analysis(file,file2,cur,db) :
         f.close()
 
 def copy_tokens(cur, tokenpath) :
-    subprocess.call(["cp " + cur  + "/" + "strcmp-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
-    subprocess.call(["cp " + cur  + "/" + "strncmp-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
-    subprocess.call(["cp " + cur  + "/" + "memcmp-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
-    subprocess.call(["cp " + cur  + "/" + "lits/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
-    subprocess.call(["cp " + cur  + "/" + "strtool-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["mv " + cur  + "/" + "strcmp-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["mv " + cur  + "/" + "strncmp-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["mv " + cur  + "/" + "memcmp-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["mv " + cur  + "/" + "lits/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["mv " + cur  + "/" + "strtool-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
     subprocess.call(["find "+tokenpath+" -size 0 -delete"],shell=True)
 
 
diff --git a/utils/autodict_ql/memcmp-strings.py b/utils/autodict_ql/memcmp-strings.py
index 2814da5b..d1047caa 100644
--- a/utils/autodict_ql/memcmp-strings.py
+++ b/utils/autodict_ql/memcmp-strings.py
@@ -40,7 +40,7 @@ def do_string_analysis(corpdir, infile1):
         for i, num1 in enumerate(lines):
             if i != 0:
                 new_lst1.append(num1)
-                print("num : %s" % num1)
+                #print("num : %s" % num1)
                 str11 = str(num1)
                 str11 = str11.replace("|","")
                 str11 = str11.replace("\n","")
diff --git a/utils/autodict_ql/stan-strings.py b/utils/autodict_ql/stan-strings.py
index 5a863f80..65d08c97 100644
--- a/utils/autodict_ql/stan-strings.py
+++ b/utils/autodict_ql/stan-strings.py
@@ -40,7 +40,7 @@ def do_string_analysis(corpdir, infile1):
         for i, num1 in enumerate(lines):
             if i != 0:
                 new_lst1.append(num1)
-                print("num : %s" % num1)
+                #print("num : %s" % num1)
                 str11 = str(num1)
                 str11 = str11.replace("|","")
                 str11 = str11.replace("\n","")
diff --git a/utils/autodict_ql/strcmp-strings.py b/utils/autodict_ql/strcmp-strings.py
index 1852b947..88128dbb 100644
--- a/utils/autodict_ql/strcmp-strings.py
+++ b/utils/autodict_ql/strcmp-strings.py
@@ -40,7 +40,7 @@ def do_string_analysis(corpdir, infile1):
         for i, num1 in enumerate(lines):
             if i != 0:
                 new_lst1.append(num1)
-                print("num : %s" % num1)
+                #print("num : %s" % num1)
                 str11 = str(num1)
                 str11 = str11.replace("|","")
                 str11 = str11.replace("\n","")
diff --git a/utils/autodict_ql/strncmp-strings.py b/utils/autodict_ql/strncmp-strings.py
index f00fa3da..0ad0e697 100644
--- a/utils/autodict_ql/strncmp-strings.py
+++ b/utils/autodict_ql/strncmp-strings.py
@@ -40,7 +40,7 @@ def do_string_analysis(corpdir, infile1):
         for i, num1 in enumerate(lines):
             if i != 0:
                 new_lst1.append(num1)
-                print("num : %s" % num1)
+                #print("num : %s" % num1)
                 str11 = str(num1)
                 str11 = str11.replace("|","")
                 str11 = str11.replace("\n","")

From 05c13588d7f6a0c8e34623eeed0b2920737ba377 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 16:22:51 +0400
Subject: [PATCH 21/25] remove dirs

remove dirs
---
 utils/autodict_ql/autodict-ql.py | 2 ++
 utils/autodict_ql/readme.md      | 3 +--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/utils/autodict_ql/autodict-ql.py b/utils/autodict_ql/autodict-ql.py
index b51fbb90..0fe7eabf 100644
--- a/utils/autodict_ql/autodict-ql.py
+++ b/utils/autodict_ql/autodict-ql.py
@@ -57,6 +57,8 @@ def copy_tokens(cur, tokenpath) :
     subprocess.call(["mv " + cur  + "/" + "memcmp-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
     subprocess.call(["mv " + cur  + "/" + "lits/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
     subprocess.call(["mv " + cur  + "/" + "strtool-strs/*" + " " + cur + "/" + tokenpath + "/."] ,shell=True)
+    subprocess.call(["rm -rf strcmp-strs memcmp-strs strncmp-strs lits strtool-strs"],shell=True)
+    subprocess.call(["rm *.out"],shell=True)
     subprocess.call(["find "+tokenpath+" -size 0 -delete"],shell=True)
 
 
diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index ccc9b0e3..16a2a20b 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -93,7 +93,7 @@ Commands:
 Core developer of the AFL++ project Marc Heuse also developed a similar tool named `dict2file` which is a LLVM pass which can automatically extracts useful tokens, in addition with LTO instrumentation mode, this dict2file is automtically generates token extraction. `Autodict-QL` plugin gives you scripting capability and you can do whatever you want to extract from the Codebase and it's up to you. in addition it's independent from LLVM system.
 On the other hand, you can also use Google dictionaries which have been made public in May 2020, but the problem of using Google dictionaries is that they are limited to specific file format and speicifications. for example, for testing binutils and ELF file format or AVI in FFMPEG, there are no prebuilt dictionary, so it is highly recommended to use `Autodict-QL` or `Dict2File` features to automatically generating dictionaries based on the target.
 
-I've personally prefer to use `Autodict-QL` or `dict2file` rather than Google dictionaries or any other manully generated dictionaries as `Autodict-QL` and `dict2file` is working based on the target.
+I've personally prefer to use `Autodict-QL` or `dict2file` rather than Google dictionaries or any other manully generated dictionaries as `Autodict-QL` and `dict2file` are working based on the target.
 In overall, fuzzing with dictionaries and well-generated tokens will give better results.
 
 There are 2 important points to remember :
@@ -101,4 +101,3 @@ There are 2 important points to remember :
 - If you combine `Autodict-QL` with AFL++ cmplog, you will get much better code coverage and hence better chance to discover new bugs.
 - Do not remember to set the `AFL_MAX_DET_EXTRAS` to the number of generated dictionaries, if you forget to set this environment variable, then AFL++ use just 200 tokens and use the rest of them probablistically. So this will guarantees that your tokens will be used by AFL++.
 
-Thanks are going to Marc Heuse, the AFL++ main developer, Antonio Morales and Stefan Nagy
\ No newline at end of file

From c4ad4681cf0aa3ff66f98053345ed7856692f25d Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 16:28:42 +0400
Subject: [PATCH 22/25] Update readme

Update readme
---
 utils/autodict_ql/readme.md | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index 16a2a20b..d8a3b014 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -78,15 +78,13 @@ Commands:
 		- `./configure --disable-shared`
 		- `codeql create database libxml-db --language=cpp --command=make`
 			- Now you have the CodeQL database of the project :-)
-3. To run the Autodict-QL, the final step is to just create a folder named `automate` in the project you want to fuzz. (inside the libxml directory)
-	- `mkdir automate` 
-4. The final step is to update the CodeQL database you created in the step 2 inside the automate dir you created at step 3 :
-	- `codeql database upgrade ../libxml-db`
-5. Everything is set! Now you should issue the following to get the tokens :
+3. The final step is to update the CodeQL database you created in the step 2 :
+	- `codeql database upgrade /home/user/libxml/libxml-db`
+4. Everything is set! Now you should issue the following to get the tokens :
 	- `python3 autodict-ql.py [CURRECT_DIR] [CODEQL_DATABASE_PATH] [TOKEN_PATH]`
-		- example : `python3 autodict-ql.py /home/user/libxml/automate /home/user/libxml/libxml-db tokens`
+		- example : `python3 /home/user/AFLplusplus/utils/autodict_ql/autodict-ql.py `pwd` /home/user/libxml/libxml-db tokens`
 			- This will create the final `tokens` dir for you and you are done, then pass the tokens path to afl `-x` flag.
-6. Done! 
+5. Done! 
 
 
 ## More on dictionaries and tokens

From 2b4e93faba3877aeb49ac873b77a930ebd6f0801 Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 16:30:58 +0400
Subject: [PATCH 23/25] Add note

Add note
---
 utils/autodict_ql/readme.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index d8a3b014..a8d252e4 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -78,7 +78,7 @@ Commands:
 		- `./configure --disable-shared`
 		- `codeql create database libxml-db --language=cpp --command=make`
 			- Now you have the CodeQL database of the project :-)
-3. The final step is to update the CodeQL database you created in the step 2 :
+3. The final step is to update the CodeQL database you created in the step 2 (Suppose we are in `aflplusplus/utils/autodict_ql/` directory) :
 	- `codeql database upgrade /home/user/libxml/libxml-db`
 4. Everything is set! Now you should issue the following to get the tokens :
 	- `python3 autodict-ql.py [CURRECT_DIR] [CODEQL_DATABASE_PATH] [TOKEN_PATH]`

From a7141b6a6ea045a20c0be7031bab0767064915ea Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 16:31:51 +0400
Subject: [PATCH 24/25] Add `

Add `
---
 utils/autodict_ql/readme.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index a8d252e4..6beba871 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -82,7 +82,7 @@ Commands:
 	- `codeql database upgrade /home/user/libxml/libxml-db`
 4. Everything is set! Now you should issue the following to get the tokens :
 	- `python3 autodict-ql.py [CURRECT_DIR] [CODEQL_DATABASE_PATH] [TOKEN_PATH]`
-		- example : `python3 /home/user/AFLplusplus/utils/autodict_ql/autodict-ql.py `pwd` /home/user/libxml/libxml-db tokens`
+		- example : `python3 /home/user/AFLplusplus/utils/autodict_ql/autodict-ql.py ``pwd`` /home/user/libxml/libxml-db tokens`
 			- This will create the final `tokens` dir for you and you are done, then pass the tokens path to afl `-x` flag.
 5. Done! 
 

From d35a90101f1ae51fa022332828209139a7e070ad Mon Sep 17 00:00:00 2001
From: microsvuln <55649192+Microsvuln@users.noreply.github.com>
Date: Sat, 3 Apr 2021 16:33:56 +0400
Subject: [PATCH 25/25] change cur

change current dir
---
 utils/autodict_ql/readme.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/utils/autodict_ql/readme.md b/utils/autodict_ql/readme.md
index 6beba871..8c24d65c 100644
--- a/utils/autodict_ql/readme.md
+++ b/utils/autodict_ql/readme.md
@@ -82,7 +82,7 @@ Commands:
 	- `codeql database upgrade /home/user/libxml/libxml-db`
 4. Everything is set! Now you should issue the following to get the tokens :
 	- `python3 autodict-ql.py [CURRECT_DIR] [CODEQL_DATABASE_PATH] [TOKEN_PATH]`
-		- example : `python3 /home/user/AFLplusplus/utils/autodict_ql/autodict-ql.py ``pwd`` /home/user/libxml/libxml-db tokens`
+		- example : `python3 /home/user/AFLplusplus/utils/autodict_ql/autodict-ql.py $PWD /home/user/libxml/libxml-db tokens`
 			- This will create the final `tokens` dir for you and you are done, then pass the tokens path to afl `-x` flag.
 5. Done!