Makes transformer script executable via cli

transform/main.py

@@ -1,4 +1,5 @@
 #! python3
+import argparse
 import logging
 import os
 import sqlite3
@@ -23,9 +24,10 @@ logging.basicConfig(
 logger = logging.getLogger("knack-transform")
 
 
-def setup_database_connection():
+def setup_database_connection(db_path=None):
     """Create connection to the SQLite database."""
-    db_path = os.environ.get('DB_PATH', '/data/knack.sqlite')
+    if db_path is None:
+        db_path = os.environ.get('DB_PATH', '/data/knack.sqlite')
     logger.info(f"Connecting to database: {db_path}")
     return sqlite3.connect(db_path)
 
@@ -35,13 +37,12 @@ def table_exists(tablename: str, con: sqlite3.Connection):
     query = "SELECT 1 FROM sqlite_master WHERE type='table' AND name=? LIMIT 1"
     return len(con.execute(query, [tablename]).fetchall()) > 0
 
-
-def main():
-    """Main entry point for the transform pipeline."""
-    logger.info("Starting transform pipeline")
+def run_from_database(db_path=None):
+    """Run the pipeline using database as input and output."""
+    logger.info("Starting transform pipeline (database mode)")
     
     try:
-        con = setup_database_connection()
+        con = setup_database_connection(db_path)
         logger.info("Database connection established")
         
         # Check if posts table exists
@@ -73,8 +74,9 @@ def main():
         max_workers = int(os.environ.get('MAX_WORKERS', 4))
         
         pipeline = create_default_pipeline(device=device, max_workers=max_workers)
+        effective_db_path = db_path or os.environ.get('DB_PATH', '/data/knack.sqlite')
         results = pipeline.run(
-            db_path=os.environ.get('DB_PATH', '/data/knack.sqlite'),
+            db_path=effective_db_path,
             initial_context=context,
             fail_fast=False  # Continue even if some nodes fail
         )
@@ -97,6 +99,49 @@ def main():
             con.close()
             logger.info("Database connection closed")
 
+def main():
+    """Main entry point with command-line argument support."""
+    parser = argparse.ArgumentParser(
+        description='Transform pipeline for Knack scraper data',
+        formatter_class=argparse.RawDescriptionHelpFormatter,
+        epilog="""
+Examples:
+  # Run with database (Docker mode)
+  python main.py
+  
+  # Run with custom device and workers
+  python main.py --database /path/to/knack.sqlite --device mps --workers 8
+  
+  # Run with specific database file
+  python main.py --database /path/to/knack.sqlite
+        """
+    )
+    
+    parser.add_argument(
+        '--database',
+        help='Path to SQLite database (for database mode). Defaults to DB_PATH env var or /data/knack.sqlite'
+    )
+    parser.add_argument(
+        '--device',
+        default=os.environ.get('COMPUTE_DEVICE', 'cpu'),
+        choices=['cpu', 'cuda', 'mps'],
+        help='Device to use for compute-intensive operations (default: cpu)'
+    )
+    parser.add_argument(
+        '--workers',
+        type=int,
+        default=int(os.environ.get('MAX_WORKERS', 4)),
+        help='Maximum number of parallel workers (default: 4)'
+    )
+    
+    args = parser.parse_args()
+    
+    # Determine mode based on arguments
+    if args.database:
+        # Database mode (original behavior)
+        run_from_database(db_path=args.database)
+        logger.info("Database connection closed")
+
 
 if __name__ == "__main__":
     main()