fix github clone to folder gitclone

gitclone/enterprise

@@ -0,0 +1 @@
+Subproject commit 38276c9a237a1779ce7a3e6f31102ff615691690

gitclone/odoo

@@ -0,0 +1 @@
+Subproject commit 8678e1c777b1faec23d4e7fd311c8ec96041f5b7

src/dataset_processor.py

@@ -133,8 +133,11 @@ class DatasetProcessor:
         Returns:
             List of code samples with metadata
         """
-        temp_dir = tempfile.mkdtemp()
-        self.temp_dirs.append(temp_dir)
+        # Create a persistent directory for cloned repositories
+        gitclone_dir = Path("./gitclone")
+        gitclone_dir.mkdir(exist_ok=True)
+        temp_dir = str(gitclone_dir)
+        # Note: We don't add this to temp_dirs since we want to keep it
 
         depth = 1
         branch = "18.0"
@@ -143,7 +146,7 @@ class DatasetProcessor:
             # Clone repository
             repo_name = repo_url.split('/')[-1].replace('.git', '')
             repo_path = os.path.join(temp_dir, repo_name)
-
+            if not os.path.exists(repo_path):
                 self.logger.info(f"Cloning {repo_url} to {repo_path}")
 
                 # Use token for private repositories if provided
@@ -175,7 +178,8 @@ class DatasetProcessor:
             return code_samples
 
         finally:
-            # Cleanup
+            # Cleanup temporary directories, but keep gitclone folder
+            if temp_dir != "./gitclone":
                 shutil.rmtree(temp_dir, ignore_errors=True)
 
     def _extract_code_samples(self, repo_path: str, config: AppConfig) -> List[Dict]: