Update app.py

app.py

@@ -1,44 +1,53 @@
-import requests
+import os
+import subprocess
 import gradio as gr
-import json
 
-def get_file_summary(file_info):
+def clone_repo(url, repo_dir):
+    env = os.environ.copy()
+    env['GIT_LFS_SKIP_SMUDGE'] = '1'
+    result = subprocess.run(["git", "clone", url, repo_dir], env=env, capture_output=True, text=True)
+    if result.returncode != 0:
+        return False, result.stderr
+    return True, None
+
+def get_file_summary(file_path):
+    size = os.path.getsize(file_path)
+    file_type = "binary" if size > 1024 * 1024 else "text"
     return {
-        "name": file_info['path'],
-        "type": "binary" if file_info['size'] > 1024 * 1024 else "text",
-        "size": file_info['size'],
+        "name": os.path.relpath(file_path),
+        "type": file_type,
+        "size": size,
     }
 
+def read_file_content(file_path):
+    with open(file_path, "r") as file:
+        return file.read()
+
 def extract_repo_content(url):
-    if "huggingface.co" not in url:
-        return [{"header": {"name": "Error", "type": "error", "size": 0}, "content": "Invalid URL. Please provide a valid Hugging Face URL."}]
-    
-    repo_name = url.split('/')[-2]
-    repo_type = url.split('/')[-3]
-    api_url = f"https://huggingface.co/api/{repo_type}/{repo_name}/tree/main"
+    repo_dir = "./temp_repo"
+    if os.path.exists(repo_dir):
+        subprocess.run(["rm", "-rf", repo_dir])
     
-    response = requests.get(api_url)
-    if response.status_code != 200:
-        return [{"header": {"name": "Error", "type": "error", "size": 0}, "content": f"Failed to fetch repository content. Status code: {response.status_code}"}]
+    success, error = clone_repo(url, repo_dir)
+    if not success:
+        return [{"header": {"name": "Error", "type": "error", "size": 0}, "content": error}]
     
-    repo_content = response.json()
     extracted_content = []
-    
-    for file_info in repo_content:
-        file_summary = get_file_summary(file_info)
-        content = {"header": file_summary}
-        
-        if file_summary["type"] == "text" and file_summary["size"] <= 1024 * 1024:
-            file_url = f"https://huggingface.co/{repo_type}/{repo_name}/resolve/main/{file_info['path']}"
-            file_response = requests.get(file_url)
-            if file_response.status_code == 200:
-                content["content"] = file_response.text
+    for root, _, files in os.walk(repo_dir):
+        for file in files:
+            file_path = os.path.join(root, file)
+            file_summary = get_file_summary(file_path)
+            content = {"header": file_summary}
+            
+            if file_summary["type"] == "text" and file_summary["size"] <= 1024 * 1024:
+                try:
+                    content["content"] = read_file_content(file_path)
+                except Exception as e:
+                    content["content"] = f"Failed to read file content: {str(e)}"
             else:
-                content["content"] = "Failed to fetch file content."
-        else:
-            content["content"] = "File too large or binary, content not captured."
-        
-        extracted_content.append(content)
+                content["content"] = "File too large or binary, content not captured."
+            
+            extracted_content.append(content)
     
     return extracted_content