Merge pull request #220 from TrellixVulnTeam/master

CVE-2007-4559 Patch

scripts/train_recognizer_synthtext90_multigpu.py

@@ -51,7 +51,26 @@ def download_extract_and_process_dataset(data_path):
     if not os.path.isdir(extraction_directory):
         print("Extracting files.")
         with tarfile.open(os.path.join(data_path, "mjsynth.tar.gz")) as tfile:
-            tfile.extractall(data_path)
+            def is_within_directory(directory, target):
+
+                abs_directory = os.path.abspath(directory)
+                abs_target = os.path.abspath(target)
+
+                prefix = os.path.commonprefix([abs_directory, abs_target])
+
+                return prefix == abs_directory
+
+            def safe_extract(tar, path=".", members=None, *, numeric_owner=False):
+
+                for member in tar.getmembers():
+                    member_path = os.path.join(path, member.name)
+                    if not is_within_directory(path, member_path):
+                        raise Exception("Attempted Path Traversal in Tar File")
+
+                tar.extractall(path, members, numeric_owner=numeric_owner) 
+
+
+            safe_extract(tfile, data_path)
 
 
 def get_image_generator(filepaths, augmenter, width, height):