import boto3
import csv
import sys

S3_BUCKET = "prod-vector-audit"
S3_PREFIX = "metadata"

def fetch_xml_from_s3(s3_client, bucket, key):
    try:
        response = s3_client.get_object(Bucket=bucket, Key=key)
        return response["Body"].read().decode("utf-8")
    except s3_client.exceptions.NoSuchKey:
        print(f"  [WARN] File not found in S3: s3://{bucket}/{key}")
        return None
    except Exception as e:
        print(f"  [ERROR] Failed to fetch s3://{bucket}/{key}: {e}")
        return None

def main(csv_path):
    s3_client = boto3.client("s3")
    missing_upc_rows = []

    with open(csv_path, newline="", encoding="utf-8") as csvfile:
        reader = csv.DictReader(csvfile)

        required_headers = {"ENCODING_QUEUE_DETAIL_ID", "FILENAME", "UPC"}
        if not required_headers.issubset(reader.fieldnames):
            print(f"[ERROR] CSV is missing required headers. Expected: {required_headers}")
            sys.exit(1)

        for row in reader:
            detail_id = row["ENCODING_QUEUE_DETAIL_ID"].strip()
            filename = row["FILENAME"].strip()
            upc = row["UPC"].strip()
            s3_key = f"{S3_PREFIX}/{filename}"
            patterns = [f"{upc}_", f"{upc}.xml", f'<ICPN IsEan="false">{upc}</ICPN>', f'<ICPN IsEan="true">{upc}</ICPN>']

            print(f"Checking ENCODING_QUEUE_DETAIL_ID={detail_id}, FILE={filename}, UPC={upc}")

            xml_content = fetch_xml_from_s3(s3_client, S3_BUCKET, s3_key)

            if xml_content is None:
                print(f"  [SKIP] Could not retrieve XML, skipping row.")
                missing_upc_rows.append({**row, "REASON": "S3 file not found or error"})
                continue

            found = any(pattern in xml_content for pattern in patterns)

            if not found:
                print(f"  [MISSING] Neither '{upc}_' nor '{upc}.xml' found in {filename}")
                missing_upc_rows.append({**row, "REASON": "All patterns not found in XML"})
            else:
                matched = [p for p in patterns if p in xml_content]
                print(f"  [OK] Found pattern(s) {matched} in {filename}")

    print(f"\n{'='*60}")
    print(f"Done. {len(missing_upc_rows)} row(s) with missing UPCs:\n")

    if missing_upc_rows:
        output_path = "missing_upc_results.csv"
        fieldnames = ["ENCODING_QUEUE_DETAIL_ID", "FILENAME", "UPC", "REASON"]
        with open(output_path, "w", newline="", encoding="utf-8") as out_csv:
            writer = csv.DictWriter(out_csv, fieldnames=fieldnames)
            writer.writeheader()
            writer.writerows(missing_upc_rows)

        for row in missing_upc_rows:
            print(f"  - ID={row['ENCODING_QUEUE_DETAIL_ID']}, FILE={row['FILENAME']}, UPC={row['UPC']} ({row['REASON']})")

        print(f"\nResults written to: {output_path}")
    else:
        print("  All UPCs were found!")

if __name__ == "__main__":
    if len(sys.argv) != 2:
        print("Usage: python check_metadata.py <path_to_csv>")
        sys.exit(1)
    main(sys.argv[1])