diff --git a/swh/lang-dectection/cloner.py b/swh/lang-dectection/cloner.py
deleted file mode 100644
index d1a7d05..0000000
--- a/swh/lang-dectection/cloner.py
+++ /dev/null
@@ -1,7 +0,0 @@
-# Copyright (C) 2015-2016  The Software Heritage developers
-# See the AUTHORS file at the top-level directory of this distribution
-# License: GNU General Public License version 3, or any later version
-# See top-level LICENSE file for more information
-        
-        
-        
diff --git a/swh/lang-dectection/ground_truth_arrange.py b/swh/lang-dectection/ground_truth_arrange.py
new file mode 100644
index 0000000..0e91b4f
--- /dev/null
+++ b/swh/lang-dectection/ground_truth_arrange.py
@@ -0,0 +1,52 @@
+# Copyright (C) 2015-2016  The Software Heritage developers
+# See the AUTHORS file at the top-level directory of this distribution
+# License: GNU General Public License version 3, or any later version
+# See top-level LICENSE file for more information
+
+#!/usr/bin/env python3
+# coding: utf-8
+
+import os
+import sys
+import io
+import json
+from shutil import copyfile
+
+def main(root):
+    
+    root_ground_truth = root + "/../ground_truth"
+    root_code_by_language = root + "/../code_by_language"
+    counts = dict()
+
+    try:
+        os.mkdir(root_code_by_language)
+    except FileExistsError:
+        pass
+        
+    for d in os.listdir(root):
+        if not d.startswith('.'):
+            ground_truth = io.open(root_ground_truth + "/" + d)
+            try:
+                j = json.load(ground_truth)
+                for k in j.keys():
+                    root_language = root_code_by_language + "/" + k
+                    try:
+                        os.mkdir(root_language)
+                    except FileExistsError:
+                        pass
+                    for f in j.get(k):
+                        counts[k] = counts.get(k, 0) + 1
+                        (_,ext) = os.path.splitext(f)
+                        new_name = str(counts[k]) + ext
+                        copy_src = root + "/" + d + "/" + f
+                        copy_des = root_language + "/" + new_name
+                        copyfile(copy_src, copy_des)
+                        print(copy_des + " successfully copied.")
+            except json.decoder.JSONDecodeError:
+                pass
+
+if __name__ == "__main__":
+    if len(sys.argv) != 2:
+        print("Only argument acceptable is a path.")
+    else:
+        main(sys.argv[1])
diff --git a/swh/lang-dectection/repo_arrange.sh b/swh/lang-dectection/repo_arrange.sh
new file mode 100755
index 0000000..18d2297
--- /dev/null
+++ b/swh/lang-dectection/repo_arrange.sh
@@ -0,0 +1,22 @@
+#!/bin/bash
+
+# This script uses linguist to get ground truth of source code identity.
+
+ROOT_FOLDER=$1
+OLDIFS=$IFS
+IFS=$'\n'
+
+if [ $# -eq 1 ]
+then
+    mkdir $ROOT_FOLDER/../ground_truth/;
+    for repo in $( ls $ROOT_FOLDER -1 );
+    do
+	echo "Generating ground truth of '$repo'";
+	linguist "$ROOT_FOLDER/$repo" --json > $ROOT_FOLDER/../ground_truth/$repo;
+	echo "Done";
+    done
+else
+    echo "Please enter root folder correctly. One folder is needed."
+fi
+
+IFS=$OLDIFS
diff --git a/swh/lang-dectection/repo_clone.sh b/swh/lang-dectection/repo_clone.sh
index 4253a2f..af4b848 100755
--- a/swh/lang-dectection/repo_clone.sh
+++ b/swh/lang-dectection/repo_clone.sh
@@ -1,23 +1,23 @@
 #!/bin/bash
 
 # This script uses git clone to get head version of git repositories.
 
 ROOT_FOLDER=$1
 OLDIFS=$IFS
 IFS=$'\n'
 
 if [ $# -eq 1 ]
 then
     for i in $( cat ../../languages );
     do
 	for url in $( cat "../../dataset/repo_lists/$i" );
 	do
 	    REPO_NAME="$(basename "$url")";
-	    git clone --depth=1 $url "$ROOT_FOLDER/$i/$REPO_NAME";
+	    git clone --depth=1 $url "$ROOT_FOLDER/$REPO_NAME";
 	done
     done
 else
     echo "Please enter root folder correctly. One folder is needed."
 fi
 
 IFS=$OLDIFS