#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Universal Data Cleaner v2 – fokus pada akurasi dan efisiensi memori.
Author  : fallenstarzz (modifikasi oleh ChatGPT)
Licence : MIT
"""

import os
import re
from datetime import datetime
from itertools import islice

# ──────────────────────────────────────────────────────────────
# 1. REGEX – pola diperketat & di-anchor
# ──────────────────────────────────────────────────────────────
PATTERNS = [
    #  https://domain.com/path:username:password
    re.compile(r'^https?://[^/]+/.+?:([^:\s]+):(.+)$', re.I),

    #  http://domain.com:username:password
    re.compile(r'^https?://[^:]+:([^:\s]+):(.+)$', re.I),

    #  domain.com:username:password
    re.compile(r'^[a-z0-9.-]+\.[a-z]{2,}:([^:\s]+):(.+)$', re.I),

    #  anythinglogin...:username:password   (login|signup|auth|register)
    re.compile(r'^[^:]*(?:login|signup|auth|register)[^:]*:([^:\s]+):(.+)$', re.I),

    #  generic three-column foo:username:password
    re.compile(r'^[^:]+:([^:\s]+):(.+)$'),
]

# ──────────────────────────────────────────────────────────────
# 2. UTILITAS
# ──────────────────────────────────────────────────────────────
def is_comment(line: str) -> bool:
    """Abaikan baris yg hanya komentar (#) – leading spasi diizinkan."""
    return not line.strip() or line.lstrip().startswith("#")


def parse_line(line: str):
    """Coba cocokkan line ke setiap pattern, kembalikan (u, p) atau None."""
    for pat in PATTERNS:
        m = pat.match(line)
        if m:
            user, pwd = m.group(1).strip(), m.group(2).strip()
            # Pastikan nilai valid & tanpa spasi / kontrol
            if user and pwd and not re.search(r'[\s\0-\x1f]', user + pwd):
                return f"{user}:{pwd}"
    return None


# ──────────────────────────────────────────────────────────────
# 3. FUNGSI UTAMA – streaming & deduplikasi
# ──────────────────────────────────────────────────────────────
def universal_data_cleaner():
    banner = "=" * 54
    print(f"{banner}\n UNIVERSAL DATA CLEANER v2\n{banner}")
    print(f"User : fallenstarzz")
    print(f"Date : {datetime.utcnow():%Y-%m-%d %H:%M:%S} UTC\n{banner}\n")

    # ── Input ░░
    src = input("📁 Nama file input: ").strip()
    if not os.path.isfile(src):
        print(f"❌ File '{src}' tidak ditemukan.")
        return

    dst = input("💾 Nama file output (enter = auto): ").strip()
    if not dst:
        base = os.path.splitext(src)[0]
        dst = f"{base}_cleaned.txt"

    print(f"\n🔄 Memproses '{src}' → '{dst}' …\n")

    total, ok = 0, 0
    skipped_preview, preview_out = [], []
    seen = set()  # deduplikasi

    try:
        with open(src, encoding="utf-8", errors="replace") as fin, \
             open(dst, "w", encoding="utf-8") as fout:

            for line in fin:
                total += 1
                if is_comment(line):
                    continue

                result = parse_line(line.rstrip("\n"))
                if result:
                    if result not in seen:
                        seen.add(result)
                        fout.write(result + "\n")
                        ok += 1
                        if ok <= 10:
                            preview_out.append(result)
                else:
                    if len(skipped_preview) < 5:
                        skipped_preview.append(line[:60])

                # Progress tiap 10 000 baris –
                if total % 10_000 == 0:
                    print(f"  … {total:,} baris → {ok:,} valid")

    except Exception as e:
        print(f"\n❌ ERROR: {e}")
        return

    # ── Ringkasan ░░
    print("\n" + banner)
    print("📊 RINGKASAN")
    print(banner)
    print(f"Total baris dibaca : {total:,}")
    print(f"Data valid tersimpan: {ok:,}")
    print(f"Duplikat dihapus    : {len(seen) - ok:,}")
    print(f"Baris terlewat      : {total - ok:,}")

    if preview_out:
        print("\n👀 Contoh output:")
        for i, v in enumerate(preview_out, 1):
            print(f"{i:2}. {v}")
        if ok > 10:
            print(f"    … dan {ok - 10} lainnya")

    if skipped_preview:
        print("\n⚠️  Contoh baris terlewat:")
        for s in skipped_preview:
            print("   ", s + ("…" if len(s) == 60 else ""))

    print("\n✅ Selesai!\n")


if __name__ == "__main__":
    universal_data_cleaner()