China Unified Social Credit Code (USCC) Validator Script Generator

# Validate China Unified Social Credit Codes (GB 32100) in a CSV export
# Reads vendor_master_export.csv, checks column TaxRegNo, writes vendor_uscc_check.csv
import csv

CHARSET = "0123456789ABCDEFGHJKLMNPQRTUWXY"
WEIGHTS = [1, 3, 9, 27, 19, 26, 16, 17, 20, 29, 25, 13, 8, 24, 10, 30, 28]


def check_uscc(raw):
    code = (raw or "").strip().upper().replace(" ", "")
    if len(code) != 18:
        return "BAD_LENGTH"
    if any(c not in CHARSET for c in code):
        return "BAD_CHARACTER"
    total = sum(CHARSET.index(c) * w for c, w in zip(code[:17], WEIGHTS))
    check = 31 - (total % 31)
    if check == 31:
        check = 0
    return "OK" if CHARSET[check] == code[17] else "BAD_CHECK_DIGIT"


with open("vendor_master_export.csv", newline="", encoding="utf-8-sig") as src:
    reader = csv.DictReader(src)
    fields = list(reader.fieldnames or []) + ["USCC_STATUS"]
    rows = []
    for row in reader:
        row["USCC_STATUS"] = check_uscc(row.get("TaxRegNo"))
        rows.append(row)

with open("vendor_uscc_check.csv", "w", newline="", encoding="utf-8-sig") as dst:
    writer = csv.DictWriter(dst, fieldnames=fields)
    writer.writeheader()
    writer.writerows(rows)

bad = [r for r in rows if r["USCC_STATUS"] != "OK"]
print(f"Checked {len(rows)} rows, {len(bad)} need review")

The code has 18 characters from a 31-character set that skips I, O, S, V and Z. Characters 1 to 17 are converted to index values, multiplied by fixed weights and summed. The check value is 31 minus the sum modulo 31, with 31 mapped to 0, and the character at that index must equal position 18.