more robust

src/transformers/file_utils.py

@@ -214,6 +214,7 @@ def cached_path(
     user_agent=None,
     extract_compressed_file=False,
     force_extract=False,
+    extract_dir=None,
 ) -> Optional[str]:
     """
     Given something that might be a URL (or might be a local path),
@@ -229,6 +230,7 @@ def cached_path(
             file in a folder along the archive.
         force_extract: if True when extract_compressed_file is True and the archive was already extracted,
             re-extract the archive and overide the folder where it was extracted.
+        extract_dir: specify a directory to extract the archive to (overwrite the default created directory).
 
     Return:
         None in case of non-recoverable file (non-existent or inaccessible url + no cache on disk).
@@ -261,7 +263,7 @@ def cached_path(
         # Something unknown
         raise ValueError("unable to parse {} as a URL or as a local path".format(url_or_filename))
 
-    if extract_compressed_file:
+    if extract_compressed_file and os.path.isfile(output_path):
         if not is_zipfile(output_path) and not tarfile.is_tarfile(output_path):
             return output_path
 
@@ -271,24 +273,22 @@ def cached_path(
         output_extract_dir_name = output_file.replace(".", "-") + "-extracted"
         output_path_extracted = os.path.join(output_dir, output_extract_dir_name)
 
-        if os.path.isdir(output_path_extracted) and os.listdir(output_path_extracted) and not force_extract:
+        if not os.path.isdir(output_path_extracted) or force_extract:
-            return output_path_extracted
+            # Extract file with a lock to prevent parallel extractions
-
+            lock_path = output_path + ".lock"
-        # Prevent parallel extractions
+            with FileLock(lock_path):
-        lock_path = output_path + ".lock"
+                shutil.rmtree(output_path_extracted, ignore_errors=True)
-        with FileLock(lock_path):
+                os.makedirs(output_path_extracted)
-            shutil.rmtree(output_path_extracted, ignore_errors=True)
+                if is_zipfile(output_path):
-            os.makedirs(output_path_extracted)
+                    with ZipFile(output_path, "r") as zip_file:
-            if is_zipfile(output_path):
+                        zip_file.extractall(output_path_extracted)
-                with ZipFile(output_path, "r") as zip_file:
+                        zip_file.close()
-                    zip_file.extractall(output_path_extracted)
+                elif tarfile.is_tarfile(output_path):
-                    zip_file.close()
+                    tar_file = tarfile.open(output_path)
-            elif tarfile.is_tarfile(output_path):
+                    tar_file.extractall(output_path_extracted)
-                tar_file = tarfile.open(output_path)
+                    tar_file.close()
-                tar_file.extractall(output_path_extracted)
+                else:
-                tar_file.close()
+                    raise EnvironmentError("Archive format of {} could not be identified".format(output_path))
-            else:
-                raise EnvironmentError("Archive format of {} could not be identified".format(output_path))
 
         return output_path_extracted