Update app.py

app.py

@@ -2,6 +2,8 @@ import json
 import uuid
 import asyncio
 import os
+import uvicorn
+from contextlib import asynccontextmanager
 from datetime import datetime, timedelta
 from urllib.parse import urlparse
 from fastapi import FastAPI, Query, BackgroundTasks
@@ -9,22 +11,45 @@ from fastapi.responses import JSONResponse
 from rapidfuzz import process, fuzz
 from cryptography.fernet import Fernet
 
-# --- 1. SETUP, ENCRYPTION & DIRECTORY ---
-# Note: Production me Fernet key ko environment variable se lena chahiye.
+# --- 1. SETUP & ENCRYPTION ---
 SECRET_KEY = Fernet.generate_key()
 cipher_suite = Fernet(SECRET_KEY)
 
-# Logs ke liye alag folder banayenge taki clean rahe
+# Logs directory setup
 LOG_DIR = "logs"
 os.makedirs(LOG_DIR, exist_ok=True)
 
-app = FastAPI(title="Fast Search API")
-
-# --- 2. LOAD DATA FROM dataset.jsonl ---
+# Global variables for dataset
 raw_data = []
 search_corpus = []
 
-def load_dataset():
+# --- 2. OPTIMIZED CLEANUP TASK ---
+async def cleanup_old_logs():
+    while True:
+        try:
+            if os.path.exists(LOG_DIR):
+                thirty_days_ago = datetime.now() - timedelta(days=30)
+                
+                for filename in os.listdir(LOG_DIR):
+                    if filename.startswith("search_logs_") and filename.endswith(".jsonl"):
+                        date_part = filename.replace("search_logs_", "").replace(".jsonl", "")
+                        try:
+                            file_date = datetime.strptime(date_part, "%Y-%m-%d")
+                            if file_date < thirty_days_ago:
+                                os.remove(os.path.join(LOG_DIR, filename))
+                                print(f"🗑️ Deleted 1-month old log file: {filename}")
+                        except ValueError:
+                            pass
+        except Exception as e:
+            print("Cleanup Error:", e)
+        
+        # Har 24 ghante me ek baar check
+        await asyncio.sleep(24 * 60 * 60)
+
+# --- 3. LIFESPAN (Replaces @app.on_event("startup")) ---
+@asynccontextmanager
+async def lifespan(app: FastAPI):
+    # a. Dataset Loading during startup
     global raw_data, search_corpus
     try:
         with open("dataset.jsonl", "r", encoding="utf-8") as f:
@@ -33,7 +58,6 @@ def load_dataset():
                     item = json.loads(line)
                     raw_data.append(item)
                     
-                    # Domain, title aur description nikal kar corpus me dalna
                     domain = urlparse(item.get("url", "")).netloc
                     text_to_search = f"{domain} {item.get('title', '')} {item.get('description', '')}"
                     search_corpus.append(text_to_search.lower())
@@ -41,16 +65,23 @@ def load_dataset():
     except FileNotFoundError:
         print("❌ ERROR: dataset.jsonl file not found in the directory!")
 
-# Load dataset when app starts
-load_dataset()
+    # b. Start background cleanup task
+    cleanup_task = asyncio.create_task(cleanup_old_logs())
+    
+    yield # App jab tak chalegi, yaha yield rahega
+    
+    # c. App shutdown hone par task cancel karna
+    cleanup_task.cancel()
+
+# Pass lifespan to FastAPI
+app = FastAPI(title="Fast Search API", lifespan=lifespan)
 
 
-# --- 3. DATE-BASED LOGGING & ENCRYPTION ---
+# --- 4. DATE-BASED LOGGING & ENCRYPTION ---
 async def log_query_encrypted(req_id: str, query: str):
     encrypted_q = cipher_suite.encrypt(query.encode()).decode()
     now = datetime.now()
     
-    # Date ke hisaab se file ka naam banega (e.g., search_logs_2026-07-22.jsonl)
     date_str = now.strftime("%Y-%m-%d")
     log_file = os.path.join(LOG_DIR, f"search_logs_{date_str}.jsonl")
     
@@ -60,43 +91,10 @@ async def log_query_encrypted(req_id: str, query: str):
         "timestamp": now.isoformat()
     }
     
-    # File me append karna (Agar file nahi hai toh khud ban jayegi)
     with open(log_file, "a", encoding="utf-8") as f:
         f.write(json.dumps(log_entry) + "\n")
 
 
-# --- 4. OPTIMIZED 1 MONTH LOG CLEANUP ---
-async def cleanup_old_logs():
-    while True:
-        try:
-            if os.path.exists(LOG_DIR):
-                thirty_days_ago = datetime.now() - timedelta(days=30)
-                
-                # Folder ki saari files check karenge
-                for filename in os.listdir(LOG_DIR):
-                    if filename.startswith("search_logs_") and filename.endswith(".jsonl"):
-                        # File ke naam se date nikalenge
-                        date_part = filename.replace("search_logs_", "").replace(".jsonl", "")
-                        try:
-                            file_date = datetime.strptime(date_part, "%Y-%m-%d")
-                            # Agar file 30 din se purani hai, toh puri file delete kar do
-                            if file_date < thirty_days_ago:
-                                os.remove(os.path.join(LOG_DIR, filename))
-                                print(f"🗑️ Deleted 1-month old log file: {filename}")
-                        except ValueError:
-                            pass
-        except Exception as e:
-            print("Cleanup Error:", e)
-        
-        # Har 24 ghante me ek baar check karega
-        await asyncio.sleep(24 * 60 * 60)
-
-@app.on_event("startup")
-async def startup_event():
-    # Background me cleanup task on startup
-    asyncio.create_task(cleanup_old_logs())
-
-
 # --- 5. FAST AI / NLP LOGIC ---
 def check_self_harm(query: str) -> bool:
     harm_keywords = ["suicide", "kill myself", "die", "harm myself", "end my life", "suiside"]
@@ -128,7 +126,7 @@ def ai_fallback_search(query: str):
 async def search(q: str = Query(..., description="Search query"), background_tasks: BackgroundTasks = BackgroundTasks()):
     req_id = str(uuid.uuid4())
     
-    # Background Logging (FastAPI wait nahi karega iske liye)
+    # Background Logging
     background_tasks.add_task(log_query_encrypted, req_id, q)
     
     # Self-Harm Check
@@ -146,7 +144,7 @@ async def search(q: str = Query(..., description="Search query"), background_tas
     
     final_results = []
     
-    # RapidFuzz search algorithm - searches in domain, title, and description
+    # RapidFuzz search algorithm
     if search_corpus:
         results = process.extract(
             q.lower(), 
@@ -157,7 +155,7 @@ async def search(q: str = Query(..., description="Search query"), background_tas
         
         for match_str, score, index in results:
             if score > 40:
-                result_item = raw_data[index].copy() # Full data return hoga including images
+                result_item = raw_data[index].copy()
                 result_item["match_score"] = round(score, 2)
                 final_results.append(result_item)
             
@@ -172,10 +170,15 @@ async def search(q: str = Query(..., description="Search query"), background_tas
         
     response_data["request_id"] = req_id
 
-    # Adult Content Header & JSON Modifier
+    # Adult Content Safety Modification
     if is_adult:
         response_data["safety_message"] = "you are safe you can do anything"
         headers = {"X-Safety-Message": "you are safe you can do anything"}
         return JSONResponse(content=response_data, headers=headers)
     
-    return response_data
+    return response_data
+
+# --- 7. START SERVER FOR GRADIO SPACE ---
+# Ye block Gradio Space ko bata dega ki port 7860 par API continuously chalani hai.
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0", port=7860)