Update file_utils.py

file_utils.py

@@ -1,51 +1,30 @@
-import os
-import subprocess
-from file_utils import validate_file_types, get_file_summary, read_file_content, summarize_content
+import gradio as gr
+from repo_utils import extract_repo_content
+from display_utils import format_output
 
-def validate_url(url):
-    return url.startswith('https://')
+# Extract and display function
+def extract_and_display(url):
+    extracted_content = extract_repo_content(url, hf_token, hf_user)
+    formatted_output = format_output(extracted_content, url)
+    return formatted_output
 
-def clone_repo(url, repo_dir, hf_token, hf_user):
-    env = os.environ.copy()
-    env['GIT_LFS_SKIP_SMUDGE'] = '1'
-    token_url = url.replace('https://', f'https://{hf_user}:{hf_token}@')
-    result = subprocess.run(["git", "clone", token_url, repo_dir], env=env, capture_output=True, text=True)
-    if result.returncode != 0:
-        return False, result.stderr
-    return True, None
+app = gr.Blocks(theme="sudeepshouche/minimalist")
 
-def extract_repo_content(url, hf_token, hf_user):
-    if not validate_url(url):
-        return [{"header": {"name": "Error", "type": "error", "size": 0}, "content": "Invalid URL"}]
+with app:
+    gr.Markdown("# Hugging Face Space / Model Repository Content Extractor")
+    url_input = gr.Textbox(label="https:// URL of Repository", placeholder="Enter the repository URL here OR select an example below...")
+    url_examples = gr.Examples(
+        examples=[
+            ["https://huggingface.co/spaces/big-vision/paligemma-hf"],
+            ["https://huggingface.co/google/paligemma-3b-mix-224"],
+            ["https://huggingface.co/microsoft/Phi-3-vision-128k-instruct"],
+            ["https://huggingface.co/llava-hf/llava-v1.6-mistral-7b-hf"]
+        ],
+        inputs=url_input
+    )
+    output_display = gr.Textbox(label="Extracted Repository Content", show_copy_button=True, lines=20, placeholder="Repository content will be extracted here...\n\nMetadata is captured for all files, but text content provided only for files less than 32 kb\n\n\n\nReview and search through the content here OR simply copy it for offline analysis!!. 🤖")
+    extract_button = gr.Button("Extract Content")
     
-    repo_dir = "./temp_repo"
-    if os.path.exists(repo_dir):
-        subprocess.run(["rm", "-rf", repo_dir])
-    
-    success, error = clone_repo(url, repo_dir, hf_token, hf_user)
-    if not success:
-        return [{"header": {"name": "Error", "type": "error", "size": 0}, "content": f"Failed to clone repository: {error}"}]
-    
-    file_types = validate_file_types(repo_dir)
-    extracted_content = []
-    for file_path, file_type in file_types.items():
-        file_summary = get_file_summary(file_path, file_type)
-        content = {"header": file_summary}
-        
-        if file_type in SUPPORTED_FILE_TYPES and file_summary["size"] <= 32 * 1024:
-            try:
-                file_content = read_file_content(file_path)
-                content["content"] = file_content
-                content["summary"] = summarize_content(file_content)
-            except Exception as e:
-                content["content"] = f"Failed to read file content: {str(e)}"
-                content["summary"] = ""
-        else:
-            content["content"] = "File too large or binary, content not captured."
-            content["summary"] = ""
-        
-        extracted_content.append(content)
-    
-    subprocess.run(["rm", "-rf", repo_dir])
-    
-    return extracted_content
+    extract_button.click(fn=extract_and_display, inputs=url_input, outputs=output_display)
+
+app.launch()