import csv
import sys
import re

def load_strings(filename):
    with open(filename, "r", encoding="utf-8", errors="ignore") as f:
        return [line.strip() for line in f if line.strip()]

def parse_datetime(raw):
    ts = raw[:14]
    return f"{ts[0:4]}-{ts[4:6]}-{ts[6:8]} {ts[8:10]}:{ts[10:12]}:{ts[12:14]}"

def extract_datetimes(values):
    """在当前记录的所有字段里提取时间戳"""
    times = []
    for v in values:
        m = re.findall(r"(20\d{12,14})", v)
        for raw in m:
            times.append(parse_datetime(raw))
    reg = times[0] if len(times) > 0 else ""
    exp = times[1] if len(times) > 1 else ""
    return reg, exp

def is_noise(s):
    if s.lower() in ("infimum", "supremum"):
        return True
    if s.startswith("==="):
        return True
    if len(s) < 2:
        return True
    return False

def looks_like_order_no(s):
    if re.match(r"AGMS\d+(-\d+)?", s):
        return True
    if re.match(r"GMS\d+-\d+", s):
        return True
    if re.fullmatch(r"\d{12,}", s):
        return True
    return False

def group_records(strings):
    records = []
    buffer = []
    for s in strings:
        if is_noise(s):
            continue
        buffer.append(s)

        if len(buffer) >= 2:  # 至少有 machineID 和 key
            machineID = buffer[0]
            key = buffer[1]
            order_no = ""

            # 在剩余字段里找 order_no
            for v in buffer[2:]:
                if looks_like_order_no(v):
                    order_no = v
                    break

            reg, exp = extract_datetimes(buffer)

            records.append([machineID, key, reg, exp, order_no])
            buffer = []
    return records

if __name__ == "__main__":
    if len(sys.argv) < 3:
        print("用法: python3 recover_table_linewise.py <输出CSV文件> <strings文件...>")
        sys.exit(1)

    out_csv = sys.argv[1]
    all_strings = []
    for fname in sys.argv[2:]:
        all_strings.extend(load_strings(fname))

    records = group_records(all_strings)

    with open(out_csv, "w", newline="", encoding="utf-8") as f:
        writer = csv.writer(f)
        writer.writerow(["machineID", "key", "register_time", "expire_time", "order_no"])
        writer.writerows(records)

    print(f"已生成 {out_csv}，共 {len(records)} 条记录")