import os, sys, argparse, time, psycopg2
from util.var import BATCH_SIZE, BUCKET_LIST, TAXONOMY_ORDER, MAJOR_RANKS
from util.output import write_csv, print_report
from util.processing import tax_lump_batch_modified, process_bam_optimized, process_batch
from dotenv import load_dotenv

conn = None
def parse_args():
    parser = argparse.ArgumentParser(description="Report on BAM Contents for Control purposes")
    parser.add_argument('-i','--input', help='Input Bam/Sam file', required=True)
    parser.add_argument('-o', "--output", help="Choose a name for the output file", required=True)
    parser.add_argument('-t', "--tax_level", help="'family', 'genus', 'species', etc.", required=True)
    parser.add_argument('-d', '--damage', help="Record damage values such as those reported by PMDTools (DS:Z tag)", action='store_true', required=False, default=False)
    parser.add_argument('-p', '--primary', help="Record only primary alignments for each read", action='store_true', required=False, default=False)
    return parser.parse_args()

if __name__ == "__main__":
    start_time = time.time()
    load_dotenv()

    # Initialize DB Connection
    try:
        conn = psycopg2.connect(dbname=os.getenv("DB_NAME"), user=os.getenv("DB_USER"), password=os.getenv("DB_PASS"))
    except Exception as e:
        print(f"Could not connect to database: {e}. Check connection parameters.")

    # Parse arguments
    args = parse_args()
    input_file = args.input
    target_level = args.tax_level.lower()

    # Get sample ID from filename
    sample_id = os.path.basename(input_file).split(".")[0]
    output_file = f"{sample_id}-{target_level}-fulltax.csv"

    if args.output != None:
        output_file = args.output

    # Validate DB connection and filesystem
    if not conn:
        print("Could not connect to database. Exiting.")
        sys.exit(1)
    if not os.path.exists(input_file):
        print(f"Input file {input_file} does not exist.")
        sys.exit(1)
    if os.path.exists(output_file):
        print(f"Output file {output_file} already exists. Exiting.")
        sys.exit(1)

    # Process and write results
    data, total_reads, lineage_lookup = process_bam_optimized(input_file, target_level, args.primary, conn)

    if total_reads > 0:
        write_csv(data, output_file, sample_id, total_reads, lineage_lookup, target_level, args.damage, conn)
        exec_time = round(time.time() - start_time, 2)
        print("Done.\n\n")
        print_report(data, total_reads, input_file, output_file, exec_time, target_level)
    else:
        print(f"No reads found in {input_file} or processing failed.")

    # Exit
    if conn:
        conn.close()
