Update app.py

app.py

@@ -1,144 +1,101 @@
 import os
 import json
 import subprocess
-from fastapi import FastAPI, Query
-from fastapi.responses import JSONResponse
 import tempfile
+from fastapi import FastAPI, Query
 
-app = FastAPI(title="Hitek Search Engine", developer="Gopal Parmar")
+app = FastAPI(title="Hitek Direct Extract API", developer="Gopal Parmar")
 
 MOUNT_PATH = "/data/"
-PART_PREFIX = "hitek.7z."
-PARTS = [f"{PART_PREFIX}{i:03d}" for i in range(1, 58)]
-EXTRACTED_JSON = "/data/users_data.json"
-MERGED_FILE = "/data/merged.7z"
-
-# ========== MERGE ALL PARTS ==========
-def merge_parts():
-    """Merge all 57 parts into a single 7z file"""
-    if os.path.exists(MERGED_FILE):
-        return True
-    
-    try:
-        with open(MERGED_FILE, 'wb') as out:
-            for part in PARTS:
-                part_path = os.path.join(MOUNT_PATH, part)
-                if os.path.exists(part_path):
-                    with open(part_path, 'rb') as f:
-                        out.write(f.read())
-                    print(f"➕ Merged: {part}")
-                else:
-                    print(f"❌ Missing: {part}")
-                    return False
-        print(f"✅ Merged: {MERGED_FILE} ({os.path.getsize(MERGED_FILE)/(1024**3):.2f} GB)")
-        return True
-    except Exception as e:
-        print(f"❌ Merge error: {e}")
-        return False
+FIRST_PART = "hitek.7z.001"
+OUTPUT_JSON = "/data/users_data.json"
 
-# ========== EXTRACT JSON ==========
-def extract_json():
-    """Extract users_data.json from merged 7z"""
-    if os.path.exists(EXTRACTED_JSON):
-        return True
-    
-    if not os.path.exists(MERGED_FILE):
-        return False
+def extract_json_direct():
+    """Extract users_data.json directly from multi-part archive"""
+    part_path = os.path.join(MOUNT_PATH, FIRST_PART)
+    if not os.path.exists(part_path):
+        return False, "First part not found"
     
     try:
-        # Use 7z command to extract
+        # 7z will automatically find all parts in the same directory
         result = subprocess.run(
-            ["7z", "x", "-so", MERGED_FILE, "users_data.json"],
+            ["7z", "x", "-so", part_path, "users_data.json"],
             capture_output=True,
             timeout=600  # 10 minutes
         )
-        if result.returncode == 0:
-            with open(EXTRACTED_JSON, 'wb') as f:
+        
+        if result.returncode == 0 and result.stdout:
+            with open(OUTPUT_JSON, 'wb') as f:
                 f.write(result.stdout)
-            print(f"✅ Extracted: {EXTRACTED_JSON} ({os.path.getsize(EXTRACTED_JSON)/(1024**2):.2f} MB)")
-            return True
+            return True, "Extracted successfully"
         else:
-            print(f"❌ Extract error: {result.stderr.decode()}")
-            return False
+            return False, result.stderr.decode()
+    except subprocess.TimeoutExpired:
+        return False, "Extraction timed out"
     except Exception as e:
-        print(f"❌ Extract error: {e}")
-        return False
+        return False, str(e)
 
-# ========== SEARCH IN JSON ==========
-def search_json(query: str, limit: int = 10):
-    """Search query in JSON file"""
-    if not os.path.exists(EXTRACTED_JSON):
-        return []
-    
-    results = []
-    try:
-        with open(EXTRACTED_JSON, 'r', encoding='utf-8', errors='ignore') as f:
-            for line in f:
-                if query in line:
-                    try:
-                        results.append(json.loads(line))
-                    except:
-                        results.append({"raw": line.strip()})
-                    if len(results) >= limit:
-                        break
-    except Exception as e:
-        return [{"error": str(e)}]
-    
-    return results
-
-# ========== API ENDPOINTS ==========
 @app.on_event("startup")
 async def startup():
-    """Run merge and extract on startup"""
-    print("🔍 Checking files...")
-    if merge_parts():
-        extract_json()
+    print("🔍 Checking for parts...")
+    # Check if first part exists
+    part_path = os.path.join(MOUNT_PATH, FIRST_PART)
+    if os.path.exists(part_path):
+        print(f"✅ Found: {FIRST_PART}")
+        print("⏳ Extracting users_data.json (this may take time)...")
+        success, msg = extract_json_direct()
+        if success:
+            size = os.path.getsize(OUTPUT_JSON) / (1024**2)
+            print(f"✅ Extracted: users_data.json ({size:.2f} MB)")
+        else:
+            print(f"❌ Extraction failed: {msg}")
     else:
-        print("❌ Merge failed. Check if all parts are mounted.")
+        print(f"❌ {FIRST_PART} not found in {MOUNT_PATH}")
 
 @app.get("/")
 async def root():
-    file_exists = os.path.exists(EXTRACTED_JSON)
+    exists = os.path.exists(OUTPUT_JSON)
     return {
-        "message": "🔍 Hitek Search Engine",
+        "message": "🔍 Hitek Direct Extract API",
         "developer": "Gopal Parmar",
-        "status": "ready" if file_exists else "processing",
-        "file_size_gb": round(os.path.getsize(EXTRACTED_JSON)/(1024**3), 2) if file_exists else 0,
-        "endpoints": {
-            "/search?q=9999999998": "Search by phone number",
-            "/status": "Check merge/extract status"
-        }
+        "status": "ready" if exists else "processing",
+        "file_size_mb": round(os.path.getsize(OUTPUT_JSON) / (1024**2), 2) if exists else 0
     }
 
 @app.get("/status")
 async def status():
-    parts_available = []
-    for part in PARTS:
+    parts_found = []
+    for i in range(1, 58):
+        part = f"hitek.7z.{i:03d}"
         if os.path.exists(os.path.join(MOUNT_PATH, part)):
-            parts_available.append(part)
+            parts_found.append(part)
     
     return {
         "developer": "Gopal Parmar",
-        "total_parts": 57,
-        "available_parts": len(parts_available),
-        "merged_file_exists": os.path.exists(MERGED_FILE),
-        "json_exists": os.path.exists(EXTRACTED_JSON),
-        "json_size_gb": round(os.path.getsize(EXTRACTED_JSON)/(1024**3), 2) if os.path.exists(EXTRACTED_JSON) else 0,
-        "status": "ready" if os.path.exists(EXTRACTED_JSON) else "processing"
+        "parts_found": len(parts_found),
+        "total_expected": 57,
+        "json_exists": os.path.exists(OUTPUT_JSON),
+        "json_size_mb": round(os.path.getsize(OUTPUT_JSON) / (1024**2), 2) if os.path.exists(OUTPUT_JSON) else 0
     }
 
 @app.get("/search")
 async def search(q: str = Query(..., min_length=4), limit: int = 10):
-    """Search by phone number or any field"""
-    results = search_json(q, limit)
+    if not os.path.exists(OUTPUT_JSON):
+        return {"error": "JSON not extracted yet. Check /status"}
     
-    if not results:
-        return {
-            "developer": "Gopal Parmar",
-            "query": q,
-            "count": 0,
-            "results": []
-        }
+    results = []
+    try:
+        with open(OUTPUT_JSON, 'r', encoding='utf-8', errors='ignore') as f:
+            for line in f:
+                if q in line:
+                    try:
+                        results.append(json.loads(line))
+                    except:
+                        results.append({"raw": line.strip()})
+                    if len(results) >= limit:
+                        break
+    except Exception as e:
+        return {"error": str(e)}
     
     return {
         "developer": "Gopal Parmar",